GuardSym : RNAm analysis
Mael Castin, Diego Santos Garcia
mai 05, 2025
##Deseq2
library(tximport)
library(readr)
library(DESeq2)## Le chargement a nécessité le package : S4Vectors## Le chargement a nécessité le package : stats4## Le chargement a nécessité le package : BiocGenerics##
## Attachement du package : 'BiocGenerics'## Les objets suivants sont masqués depuis 'package:stats':
##
## IQR, mad, sd, var, xtabs## Les objets suivants sont masqués depuis 'package:base':
##
## anyDuplicated, aperm, append, as.data.frame, basename, cbind,
## colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
## get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
## match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
## Position, rank, rbind, Reduce, rownames, sapply, saveRDS, setdiff,
## table, tapply, union, unique, unsplit, which.max, which.min##
## Attachement du package : 'S4Vectors'## L'objet suivant est masqué depuis 'package:utils':
##
## findMatches## Les objets suivants sont masqués depuis 'package:base':
##
## expand.grid, I, unname## Le chargement a nécessité le package : IRanges##
## Attachement du package : 'IRanges'## L'objet suivant est masqué depuis 'package:grDevices':
##
## windows## Le chargement a nécessité le package : GenomicRanges## Le chargement a nécessité le package : GenomeInfoDb## Le chargement a nécessité le package : SummarizedExperiment## Le chargement a nécessité le package : MatrixGenerics## Le chargement a nécessité le package : matrixStats##
## Attachement du package : 'MatrixGenerics'## Les objets suivants sont masqués depuis 'package:matrixStats':
##
## colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,
## colCounts, colCummaxs, colCummins, colCumprods, colCumsums,
## colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,
## colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,
## colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,
## colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,
## colWeightedMeans, colWeightedMedians, colWeightedSds,
## colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,
## rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,
## rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,
## rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,
## rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,
## rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,
## rowWeightedMads, rowWeightedMeans, rowWeightedMedians,
## rowWeightedSds, rowWeightedVars## Le chargement a nécessité le package : Biobase## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.##
## Attachement du package : 'Biobase'## L'objet suivant est masqué depuis 'package:MatrixGenerics':
##
## rowMedians## Les objets suivants sont masqués depuis 'package:matrixStats':
##
## anyMissing, rowMedianslibrary(rhdf5)
library(readxl)
library(readr)
library(dplyr)##
## Attachement du package : 'dplyr'## L'objet suivant est masqué depuis 'package:Biobase':
##
## combine## L'objet suivant est masqué depuis 'package:matrixStats':
##
## count## Les objets suivants sont masqués depuis 'package:GenomicRanges':
##
## intersect, setdiff, union## L'objet suivant est masqué depuis 'package:GenomeInfoDb':
##
## intersect## Les objets suivants sont masqués depuis 'package:IRanges':
##
## collapse, desc, intersect, setdiff, slice, union## Les objets suivants sont masqués depuis 'package:S4Vectors':
##
## first, intersect, rename, setdiff, setequal, union## Les objets suivants sont masqués depuis 'package:BiocGenerics':
##
## combine, intersect, setdiff, union## Les objets suivants sont masqués depuis 'package:stats':
##
## filter, lag## Les objets suivants sont masqués depuis 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)
library(ggpubr)
library(plotrix)
library(vsn)
library(pheatmap)
library(RColorBrewer)
library(ggfortify)
library(FactoMineR)
library(factoextra)## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBalibrary(gridExtra)##
## Attachement du package : 'gridExtra'## L'objet suivant est masqué depuis 'package:dplyr':
##
## combine## L'objet suivant est masqué depuis 'package:Biobase':
##
## combine## L'objet suivant est masqué depuis 'package:BiocGenerics':
##
## combinelibrary(eba)
library(ade4)##
## Attachement du package : 'ade4'## L'objet suivant est masqué depuis 'package:FactoMineR':
##
## reconst## L'objet suivant est masqué depuis 'package:GenomicRanges':
##
## score## L'objet suivant est masqué depuis 'package:BiocGenerics':
##
## score##TopGO et ClusterProfiler
library(DESeq2)
library(ggplot2)
library(dplyr)
library(readr)
library(Rgraphviz)## Le chargement a nécessité le package : graph## Le chargement a nécessité le package : grid##
## Attachement du package : 'Rgraphviz'## Les objets suivants sont masqués depuis 'package:IRanges':
##
## from, to## Les objets suivants sont masqués depuis 'package:S4Vectors':
##
## from, tolibrary(topGO)## Le chargement a nécessité le package : GO.db## Le chargement a nécessité le package : AnnotationDbi##
## Attachement du package : 'AnnotationDbi'## L'objet suivant est masqué depuis 'package:dplyr':
##
## select## ## Le chargement a nécessité le package : SparseM##
## groupGOTerms: GOBPTerm, GOMFTerm, GOCCTerm environments built.##
## Attachement du package : 'topGO'## L'objet suivant est masqué depuis 'package:grid':
##
## depth## L'objet suivant est masqué depuis 'package:IRanges':
##
## memberslibrary(httr)##
## Attachement du package : 'httr'## L'objet suivant est masqué depuis 'package:Biobase':
##
## contentlibrary(jsonlite)
library(clusterProfiler)## clusterProfiler v4.14.6 Learn more at https://yulab-smu.top/contribution-knowledge-mining/
##
## Please cite:
##
## G Yu. Thirteen years of clusterProfiler. The Innovation. 2024,
## 5(6):100722##
## Attachement du package : 'clusterProfiler'## L'objet suivant est masqué depuis 'package:AnnotationDbi':
##
## select## L'objet suivant est masqué depuis 'package:IRanges':
##
## slice## L'objet suivant est masqué depuis 'package:S4Vectors':
##
## rename## L'objet suivant est masqué depuis 'package:stats':
##
## filterlibrary(stringr)##
## Attachement du package : 'stringr'## L'objet suivant est masqué depuis 'package:graph':
##
## boundarylibrary(tibble)
library(gridExtra)
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ purrr 1.0.4
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ lubridate::%within%() masks IRanges::%within%()
## ✖ stringr::boundary() masks graph::boundary()
## ✖ dplyr::collapse() masks IRanges::collapse()
## ✖ gridExtra::combine() masks dplyr::combine(), Biobase::combine(), BiocGenerics::combine()
## ✖ httr::content() masks Biobase::content()
## ✖ dplyr::count() masks matrixStats::count()
## ✖ dplyr::desc() masks IRanges::desc()
## ✖ tidyr::expand() masks S4Vectors::expand()
## ✖ clusterProfiler::filter() masks dplyr::filter(), stats::filter()
## ✖ dplyr::first() masks S4Vectors::first()
## ✖ purrr::flatten() masks jsonlite::flatten()
## ✖ dplyr::lag() masks stats::lag()
## ✖ ggplot2::Position() masks BiocGenerics::Position(), base::Position()
## ✖ purrr::reduce() masks GenomicRanges::reduce(), IRanges::reduce()
## ✖ clusterProfiler::rename() masks dplyr::rename(), S4Vectors::rename()
## ✖ lubridate::second() masks S4Vectors::second()
## ✖ lubridate::second<-() masks S4Vectors::second<-()
## ✖ clusterProfiler::select() masks AnnotationDbi::select(), dplyr::select()
## ✖ purrr::simplify() masks clusterProfiler::simplify()
## ✖ clusterProfiler::slice() masks dplyr::slice(), IRanges::slice()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors##UpSetR
library(UpSetR)
library(ComplexUpset)##
## Attachement du package : 'ComplexUpset'
##
## L'objet suivant est masqué depuis 'package:UpSetR':
##
## upsetlibrary(ggplot2)
library(dplyr)
library(tidyr)1 Deseq2 analysis
1.1 Plant
1.1.1 Import des données pour l’analyse Deseq2 sur les échantillons issus des plantes
# Lire la table de metadata (avec sample, condition, chemin des fichiers)
metadata <- read_excel("metadata_coldata.xlsx",
sheet = "Plant_L")
# Lire la correspondance transcript-gène
tx2gene <- read.table("rquantif/Plant/gene_to_transcript.txt", sep="\t",
header=FALSE)
tx2gene <- tx2gene[, c(2, 1)]
assoc_orga <- read.table("rquantif/assoc_orga.txt", sep=",", header=FALSE)
# Ajouter une colonne vide pour orga
tx2gene$orga <- NA
# Boucle pour faire les correspondances partiels
for (i in 1:nrow(assoc_orga)) {
pattern <- assoc_orga$V1[i]
orga_value <- assoc_orga$V2[i]
# Chercher les lignes dont transcript_id contient le pattern
match_idx <- grep(pattern, tx2gene$V2)
# Ajouter l'orga correspondante
tx2gene$orga[match_idx] <- orga_value
}
# Vérifier
head(tx2gene)## V2
## 1 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338
## 2 lcl|CAKKNF020000001.1_cds_CAH0746831.1_16339
## 3 lcl|CAKKNF020000001.1_cds_CAH0746832.1_16340
## 4 lcl|CAKKNF020000001.1_cds_CAH0746833.1_16341
## 5 lcl|CAKKNF020000001.1_cds_CAH0746834.1_16342
## 6 lcl|CAKKNF020000001.1_cds_CAH0746835.1_16343
## V1 orga
## 1 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 Bemisia
## 2 lcl|CAKKNF020000001.1_cds_CAH0746831.1_16339 Bemisia
## 3 lcl|CAKKNF020000001.1_cds_CAH0746832.1_16340 Bemisia
## 4 lcl|CAKKNF020000001.1_cds_CAH0746833.1_16341 Bemisia
## 5 lcl|CAKKNF020000001.1_cds_CAH0746834.1_16342 Bemisia
## 6 lcl|CAKKNF020000001.1_cds_CAH0746835.1_16343 Bemisia# Charger les fichiers dans tximport
files <- setNames(metadata$file, metadata$sample)
tx2gene$orga <- trimws(tx2gene$orga)
tx2gene_tomato = subset(tx2gene, orga == "Tomato")
tx2gene_virus = subset(tx2gene, orga == "TYLCV")
h5closeAll()
txi_tomato <- tximport(files, type="kallisto", tx2gene = tx2gene_tomato,
ignoreTxVersion=FALSE)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
## transcripts missing from tx2gene: 28329
## summarizing abundance
## summarizing counts
## summarizing length
## summarizing inferential replicateshead(txi_tomato$counts)## P1L P2L P3L P4L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 20.000 31.000 68.500 21.0000
## lcl|NC_007898.3_cds_YP_008563068.1_44306 1682.668 1923.747 1355.941 774.0872
## lcl|NC_007898.3_cds_YP_008563069.1_44307 0.000 0.000 0.000 0.0000
## lcl|NC_007898.3_cds_YP_008563070.1_44308 104.000 172.000 132.000 99.0000
## lcl|NC_007898.3_cds_YP_008563071.1_44309 212.000 302.000 200.000 314.0000
## lcl|NC_007898.3_cds_YP_008563072.1_44310 148.000 353.000 54.000 187.0000
## P5L P6L P7L P8L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 15.0000 26.00 28.0000 30.50
## lcl|NC_007898.3_cds_YP_008563068.1_44306 658.9715 1846.49 808.8525 1571.64
## lcl|NC_007898.3_cds_YP_008563069.1_44307 0.0000 0.00 0.0000 0.00
## lcl|NC_007898.3_cds_YP_008563070.1_44308 71.0000 112.00 73.0000 76.00
## lcl|NC_007898.3_cds_YP_008563071.1_44309 116.0000 387.00 228.0000 151.00
## lcl|NC_007898.3_cds_YP_008563072.1_44310 132.0000 179.00 171.0000 85.00
## P9L P10L P11L P12L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 43.500 31.500 20.000 31.000
## lcl|NC_007898.3_cds_YP_008563068.1_44306 1157.977 1677.013 1588.374 5712.037
## lcl|NC_007898.3_cds_YP_008563069.1_44307 0.000 0.000 0.000 0.000
## lcl|NC_007898.3_cds_YP_008563070.1_44308 142.000 118.000 115.000 424.000
## lcl|NC_007898.3_cds_YP_008563071.1_44309 359.000 374.000 170.000 172.000
## lcl|NC_007898.3_cds_YP_008563072.1_44310 228.000 201.000 96.000 326.000
## P13L P14L P15L P16L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 38.000 34.000 91.500 22.5000
## lcl|NC_007898.3_cds_YP_008563068.1_44306 954.512 1335.165 1485.537 894.2578
## lcl|NC_007898.3_cds_YP_008563069.1_44307 0.000 0.000 0.000 0.0000
## lcl|NC_007898.3_cds_YP_008563070.1_44308 116.000 86.000 199.000 67.0000
## lcl|NC_007898.3_cds_YP_008563071.1_44309 361.000 210.000 367.000 166.0000
## lcl|NC_007898.3_cds_YP_008563072.1_44310 202.000 190.000 217.000 126.0000
## P17L P18L P19L P20L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 43.500 45.500000 24.50000 56.0000
## lcl|NC_007898.3_cds_YP_008563068.1_44306 1172.157 725.754170 80.51105 991.6025
## lcl|NC_007898.3_cds_YP_008563069.1_44307 0.000 1.739267 0.00000 0.0000
## lcl|NC_007898.3_cds_YP_008563070.1_44308 153.000 118.000000 64.00000 109.0000
## lcl|NC_007898.3_cds_YP_008563071.1_44309 332.000 314.000000 215.00000 436.0000
## lcl|NC_007898.3_cds_YP_008563072.1_44310 210.000 141.000000 110.00000 200.0000
## P21L P22L P23L P24L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 51.000 30.50 41.500000 55.500
## lcl|NC_007898.3_cds_YP_008563068.1_44306 2350.673 3282.23 1028.449665 3739.596
## lcl|NC_007898.3_cds_YP_008563069.1_44307 0.000 0.00 1.628528 0.000
## lcl|NC_007898.3_cds_YP_008563070.1_44308 136.000 98.00 116.000000 167.000
## lcl|NC_007898.3_cds_YP_008563071.1_44309 428.000 274.00 494.000000 489.000
## lcl|NC_007898.3_cds_YP_008563072.1_44310 284.000 133.00 232.000000 373.000metadata_virus <- metadata[grepl("V", metadata$condition), ]
files_virus <- setNames(metadata_virus$file, metadata_virus$sample)
h5closeAll()
txi_virus <- tximport(files_virus, type="kallisto", tx2gene = tx2gene_virus,
ignoreTxVersion=FALSE)## 1 2 3 4 5 6 7 8 9 10 11 12
## transcripts missing from tx2gene: 72714
## summarizing abundance
## summarizing counts
## summarizing length
## summarizing inferential replicateshead(txi_virus$counts)## P4L P5L P6L P10L
## lcl|NC_004005.1_cds_NP_658991.1_1 766.6021 173.5676 603.2835 385.1499
## lcl|NC_004005.1_cds_NP_658992.1_2 4610.3979 1298.4324 3026.7165 1940.8501
## lcl|NC_004005.1_cds_NP_658993.1_3 435.2293 223.3472 250.8378 111.9367
## lcl|NC_004005.1_cds_NP_658994.1_4 652.7707 398.6528 464.1622 258.0633
## lcl|NC_004005.1_cds_NP_658995.1_5 429.0000 326.0000 240.3006 216.0000
## lcl|NC_004005.1_cds_NP_658996.1_6 0.0000 0.0000 8.6994 0.0000
## P11L P12L P16L P17L
## lcl|NC_004005.1_cds_NP_658991.1_1 159.3277 6.749435 11143.098 5232.300
## lcl|NC_004005.1_cds_NP_658992.1_2 1365.6723 824.250565 46933.902 27241.700
## lcl|NC_004005.1_cds_NP_658993.1_3 169.5604 197.197788 2800.160 1937.213
## lcl|NC_004005.1_cds_NP_658994.1_4 278.4396 197.802212 4308.128 2751.787
## lcl|NC_004005.1_cds_NP_658995.1_5 244.0000 83.000000 3919.711 2527.000
## lcl|NC_004005.1_cds_NP_658996.1_6 0.0000 0.000000 0.000 0.000
## P18L P22L P23L P24L
## lcl|NC_004005.1_cds_NP_658991.1_1 9633.980 3240.605 6985.227 6360.615
## lcl|NC_004005.1_cds_NP_658992.1_2 45496.020 15950.395 34657.773 42542.385
## lcl|NC_004005.1_cds_NP_658993.1_3 2863.081 1288.546 2391.800 3894.182
## lcl|NC_004005.1_cds_NP_658994.1_4 4207.919 2260.454 3444.030 5211.818
## lcl|NC_004005.1_cds_NP_658995.1_5 3602.000 2025.000 2937.170 4126.000
## lcl|NC_004005.1_cds_NP_658996.1_6 0.000 0.000 0.000 0.0001.1.2 Formalisations des données
#Tomate
dds_tomato <- DESeqDataSetFromTximport(txi_tomato, colData=metadata,
design=~condition)## Warning in DESeqDataSet(se, design = design, ignoreRank): some variables in
## design formula are characters, converting to factors## using counts and average transcript lengths from tximportdds_tomato <- dds_tomato[ rowSums(counts(dds_tomato)) > 10, ]
#Keep only genes with at least 10 count
dds_tomato.deseq.para <- DESeq(dds_tomato,fitType = "parametric")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.para <- log(mcols(dds_tomato.deseq.para)$dispGeneEst) -
log(mcols(dds_tomato.deseq.para)$dispFit)
median(abs(residual.para))## [1] 1.265786plotDispEsts(dds_tomato.deseq.para)
dds_tomato.deseq.local <- DESeq(dds_tomato,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.local <- log(mcols(dds_tomato.deseq.local)$dispGeneEst) -
log(mcols(dds_tomato.deseq.local)$dispFit)
median(abs(residual.local))## [1] 0.9909089plotDispEsts(dds_tomato.deseq.local)
dds_tomato.deseq.mean <- DESeq(dds_tomato,fitType = "mean")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.mean <- log(mcols(dds_tomato.deseq.mean)$dispGeneEst) -
log(mcols(dds_tomato.deseq.mean)$dispFit)
median(abs(residual.mean))## [1] 2.41282plotDispEsts(dds_tomato.deseq.mean)
dds_tomato.deseq <- DESeq(dds_tomato,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingdds_tomato.deseq.counts <- round(counts(dds_tomato.deseq,normalized=TRUE))
#write.csv(dds_tomato.deseq.counts,
# "rquantif/Plant/dds_tomato_deseq_counts_hisat2.txt")
#Virus
dds_virus <- DESeqDataSetFromTximport(txi_virus, colData=metadata_virus,
design=~condition)## Warning in DESeqDataSet(se, design = design, ignoreRank): some variables in
## design formula are characters, converting to factors## using counts and average transcript lengths from tximportdds_virus <- dds_virus[ rowSums(counts(dds_virus)) > 10, ]
#Keep only genes with at least 10 count
dds_virus$condition <- droplevels(dds_virus$condition)
dds_virus.deseq.para <- DESeq(dds_virus, fitType = "parametric")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.## Warning in lfproc(x, y, weights = weights, cens = cens, base = base, geth =
## geth, : Estimated rdf < 1.0; not estimating variance## final dispersion estimates## fitting model and testingresidual.para <- log(mcols(dds_virus.deseq.para)$dispGeneEst) -
log(mcols(dds_virus.deseq.para)$dispFit)
median(abs(residual.para))## [1] 0.03586308plotDispEsts(dds_virus.deseq.para)
dds_virus.deseq.local <- DESeq(dds_virus,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## Warning in lfproc(x, y, weights = weights, cens = cens, base = base, geth =
## geth, : Estimated rdf < 1.0; not estimating variance## final dispersion estimates## fitting model and testingresidual.local <- log(mcols(dds_virus.deseq.local)$dispGeneEst) -
log(mcols(dds_virus.deseq.local)$dispFit)
median(abs(residual.local))## [1] 0.03586308plotDispEsts(dds_virus.deseq.local)
dds_virus.deseq.mean <- DESeq(dds_virus,fitType = "mean")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.mean <- log(mcols(dds_virus.deseq.mean)$dispGeneEst) -
log(mcols(dds_virus.deseq.mean)$dispFit)
median(abs(residual.mean))## [1] 1.289039plotDispEsts(dds_virus.deseq.mean)
dds_virus.deseq <- DESeq(dds_virus,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## Warning in lfproc(x, y, weights = weights, cens = cens, base = base, geth =
## geth, : Estimated rdf < 1.0; not estimating variance## final dispersion estimates## fitting model and testingdds_virus.deseq.counts <- round(counts(dds_virus.deseq,normalized=TRUE))
#write.csv(dds_virus.deseq.counts,
# "rquantif/Plant/dds_virus_deseq_counts_hisat2.txt")1.1.3 Tests et représentations graphiques
vsd <- varianceStabilizingTransformation(dds_tomato, blind = FALSE)## using 'avgTxLength' from assays(dds), correcting for library sizerld <- rlog(dds_tomato, blind=FALSE)## using 'avgTxLength' from assays(dds), correcting for library sizehead(assay(vsd), 3)## P1L P2L P3L P4L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 7.063662 7.206476 7.418755 6.993896
## lcl|NC_007898.3_cds_YP_008563068.1_44306 11.151251 11.234681 10.251883 9.877188
## lcl|NC_007898.3_cds_YP_008563070.1_44308 8.029941 8.369559 7.859792 7.820386
## P5L P6L P7L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 6.982082 7.021020 7.189539
## lcl|NC_007898.3_cds_YP_008563068.1_44306 10.037657 10.808059 10.146244
## lcl|NC_007898.3_cds_YP_008563070.1_44308 7.800118 7.812033 7.739915
## P8L P9L P10L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 7.091689 7.243019 7.093312
## lcl|NC_007898.3_cds_YP_008563068.1_44306 10.603838 10.138855 10.595053
## lcl|NC_007898.3_cds_YP_008563070.1_44308 7.578648 7.974042 7.823986
## P11L P12L P13L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 7.081925 7.208884 7.243324
## lcl|NC_007898.3_cds_YP_008563068.1_44306 11.130602 12.862203 10.152165
## lcl|NC_007898.3_cds_YP_008563070.1_44308 8.150603 9.276197 7.928782
## P14L P15L P16L P17L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 7.285930 7.683955 6.908109 7.203986
## lcl|NC_007898.3_cds_YP_008563068.1_44306 10.788626 10.536555 9.671919 10.081642
## lcl|NC_007898.3_cds_YP_008563070.1_44308 7.849409 8.284181 7.395246 7.967945
## P18L P19L P20L P21L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 7.242041 6.978935 7.43112 7.373606
## lcl|NC_007898.3_cds_YP_008563068.1_44306 9.508453 7.571700 10.14196 11.251043
## lcl|NC_007898.3_cds_YP_008563070.1_44308 7.819165 7.428170 7.86061 8.027686
## P22L P23L P24L
## lcl|NC_007898.3_cds_YP_008563067.1_44305 7.195493 7.235949 7.483043
## lcl|NC_007898.3_cds_YP_008563068.1_44306 11.941074 10.061428 12.042462
## lcl|NC_007898.3_cds_YP_008563070.1_44308 7.908311 7.850255 8.291659ntd <- normTransform(dds_tomato)## using 'avgTxLength' from assays(dds), correcting for library sizecount.plot <- meanSdPlot(assay(dds_tomato))$gg
ntd.plot <- meanSdPlot(assay(ntd))$gg
vsd.plot <- meanSdPlot(assay(vsd))$gg
rld.plot <- meanSdPlot(assay(rld))$gg
ggarrange(count.plot,ntd.plot,vsd.plot,rld.plot,
labels=c("counts","ntd","vst","rlog"),ncol=2,nrow=2)
df <- bind_rows(
as_tibble(assay(ntd)[, 1:2]) %>% mutate(transformation = "ntd"),
as_tibble(assay(vsd)[, 1:2]) %>% mutate(transformation = "vst"),
as_tibble(assay(rld)[, 1:2]) %>% mutate(transformation = "rlog"))
colnames(df)[1:2] <- c("x", "y")
lvls <- c("ntd", "vst", "rlog")
df$transformation <- factor(df$transformation, levels=lvls)
g = ggplot(df, aes(x = x, y = y)) + geom_hex(bins = 80) +
coord_fixed() + facet_grid( . ~ transformation)
print(g)
select <- order(rowMeans(counts(dds_tomato.deseq,normalized=TRUE)),
decreasing=TRUE)
df <- as.data.frame(colData(dds_tomato.deseq)[,"sample"])
wss <- sapply(1:10, function(k) {
kmeans(assay(ntd)[select, ], centers = k, nstart = 10, algorithm = "Lloyd",
iter.max = 1000)$tot.withinss
})
# 1. Heatmap avec ntd
pheatmap(assay(ntd)[select,],
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = 500)
# 2. Heatmap avec vsd
pheatmap(assay(vsd)[select,],
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = 500)
# 3. Heatmap avec rld
pheatmap(assay(rld)[select,],
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = 500)
# 4. Heatmap des distances entre échantillons
sampleDists <- dist(t(assay(vsd)))
sampleDistMatrix <- as.matrix(sampleDists)
rownames(sampleDistMatrix) <- paste(vsd$condition, vsd$type, sep = "-")
colnames(sampleDistMatrix) <- NULL
colors <- colorRampPalette(rev(brewer.pal(9, "Blues")))(255)
pheatmap(sampleDistMatrix,
clustering_distance_rows = sampleDists,
clustering_distance_cols = sampleDists,
col = colors)
vst_df1 <- as.data.frame(t(assay(vsd)))
vst_df1$Treatment <- metadata$condition
pca <- prcomp(vst_df1[,1:ncol(vst_df1)-1])
# Effectuer l'analyse PCA
pca_facto <- PCA(vst_df1[,1:ncol(vst_df1)-1], graph = FALSE)
# Préparer un PDF pour sauvegarde
#pdf("rquantif/Plant/PCA_FactoMineR_Plant_results.pdf", width = 10, height = 12)
## 1. Scree plot
print(fviz_screeplot(pca_facto, addlabels = TRUE, ylim = c(0, 70)))
## 2. Représentation des individus
print(fviz_pca_ind(pca_facto, axes = c(1, 2), repel = TRUE))
## 3. Cos2 des individus - Axe 1 & 2 côte à côte
p1 <- fviz_cos2(pca_facto, choice = "ind", axes = 1,
title = "Qualité de représentation (cos2) - Axe 1")
p2 <- fviz_cos2(pca_facto, choice = "ind", axes = 2,
title = "Qualité de représentation (cos2) - Axe 2")
grid.arrange(p1, p2, ncol = 2)
## 4. Contributions des individus - Axe 1 & 2 côte à côte
p3 <- fviz_contrib(pca_facto, choice = "ind", axes = 1,
title = "Contribution des individus - Axe 1")
p4 <- fviz_contrib(pca_facto, choice = "ind", axes = 2,
title = "Contribution des individus - Axe 2")
grid.arrange(p3, p4, ncol = 2)
## 5. Représentation colorée par cos2
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), title = "Individus - Colorés par cos2"))
## 6. Représentation colorée par contribution
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2),
title = "Individus - Colorés par contribution"))
## 7. Variables les plus contributrices (Top 5)
print(fviz_pca_var(pca_facto, col.var = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), repel = TRUE,
select.var = list(contrib = 5),
title = "Variables - Top 5 contributions"))
# 1. Extraire uniquement les données numériques
X <- vst_df1[, 1:(ncol(vst_df1) - 1)]
groupes <- as.factor(vst_df1$Treatment)
# 2. Analyse en composantes principales avec dudi.pca
acp <- dudi.pca(X, scannf = FALSE, nf = 5)
# 3. Analyse entre groupes (between-class analysis)
acp_btw <- ade4:::between(acp, groupes, scannf = FALSE, nf = 5)## Warning in ade4:::between(acp, groupes, scannf = FALSE, nf = 5): To avoid some
## name conflicts, the 'between' function is now deprecated. Please use 'bca'
## instead# 4. Visualisation
s.class(acp_btw$ls, fac = groupes, col = c("steelblue", "tomato", "darkgreen"),
sub = "Projection des individus entre groupes")
# Fermer le PDF
#dev.off()
df_pca <- as.data.frame(pca$x)
df_pca$Treatment <- metadata$condition
head(df_pca)## PC1 PC2 PC3 PC4 PC5 PC6
## P1L -47.721497 -16.718596 -24.29568 15.517044 -21.316953 20.8505165
## P2L -7.776144 91.688901 -20.39078 -14.553629 1.621508 44.5101583
## P3L -79.590820 -24.985952 115.46807 -33.991554 4.939961 12.1663139
## P4L -21.450694 -4.998577 -24.42886 -1.089912 -15.790559 16.3963204
## P5L -74.153950 -28.790244 -37.69835 4.879195 35.128426 13.1148585
## P6L -11.936260 -15.044593 -15.99511 -1.673811 -37.997066 0.1654554
## PC7 PC8 PC9 PC10 PC11 PC12
## P1L 15.6981504 25.347012 -10.422114 -0.8932647 7.840784 6.814074
## P2L -11.7791161 -9.503607 -13.468573 -5.8593826 -16.923205 -22.067135
## P3L -5.4523083 1.334541 6.891136 1.8821953 -8.530346 2.724801
## P4L 1.5401095 6.874333 19.122595 0.7707734 5.862071 17.100817
## P5L -9.2204986 -2.647387 -4.689710 8.0829171 9.637693 20.803175
## P6L 0.8109608 7.265476 13.644624 7.2722881 -14.137346 4.314608
## PC13 PC14 PC15 PC16 PC17 PC18
## P1L 5.805118 21.1783826 11.645073 -25.3649444 -1.3714993 -5.9418137
## P2L -15.464384 0.8376284 2.205112 -0.1374990 -0.1559933 1.4193702
## P3L 2.294475 3.7711934 2.283892 -0.5504851 1.0115857 -0.2391166
## P4L -10.458641 -26.6730001 19.572605 6.8170163 -1.2664933 5.8444222
## P5L -11.761873 13.0991974 -16.082145 16.0088748 -0.1293119 0.7763312
## P6L -4.793326 -2.3224832 -8.616272 6.6571989 9.5406358 8.6911042
## PC19 PC20 PC21 PC22 PC23 PC24
## P1L -0.6653093 -2.8500083 -1.815240 0.1169869 0.3158526 1.264389e-13
## P2L 1.0888365 0.7219588 -0.554614 0.9957477 -0.2807660 -3.402869e-13
## P3L 0.5645408 -0.5701483 2.130396 -1.8498739 -1.6033081 3.989092e-14
## P4L 8.1667135 -7.6844202 15.075258 -2.4564095 -2.4295560 1.151172e-13
## P5L 3.8643069 5.0572379 -3.097019 6.6563617 1.4055893 -9.513108e-14
## P6L -27.2601324 8.5459262 -11.525632 -6.7461873 5.4166250 1.557680e-13
## Treatment
## P1L P_t1_Q21L
## P2L P_t1_Q21L
## P3L P_t1_Q21L
## P4L P_t1_Q21V_L
## P5L P_t1_Q21V_L
## P6L P_t1_Q21V_Lpercentage <- round(pca$sdev^2 / sum(pca$sdev^2) * 100, 2)
percentage <- paste( colnames(df_pca), "(",
paste( as.character(percentage), "%", ")", sep="") )
g = ggplot(df_pca, aes(PC1, PC2, color=Treatment)) + geom_point(size=2) +
xlab(percentage[1]) + ylab(percentage[2]) +
theme(axis.text.x = element_text(family = "Times"),
axis.title.x = element_text(family = "Times", face = "bold"),
axis.text.y = element_text(family = "Times"),
axis.title.y = element_text(family = "Times", face = "bold"),
legend.title = element_text(family = "Times", face = "bold"),
legend.text = element_text(family = "Times")) +
scale_colour_hue(name = "Condition")
print(g)## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): famille de
## police introuvable dans la base de données des polices Windows## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): famille de
## police introuvable dans la base de données des polices Windows## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
# Calcul des loadings
loadings <- as.data.frame(pca$rotation[,1:2])
loadings$gene <- rownames(loadings)
# Pour ne garder que les 20 plus contributeurs (par ex.)
top_contributors <- loadings[order(abs(loadings$PC1) + abs(loadings$PC2),
decreasing = TRUE),][1:20,]
# Graphique biplot
ggplot(df_pca, aes(PC1, PC2), size=2) +
geom_segment(data=top_contributors, aes(x=0, y=0, xend=PC1*5, yend=PC2*5),
arrow=arrow(length=unit(0.2,"cm")), color="gray40") +
geom_text(data=top_contributors, aes(x=PC1*5, y=PC2*5, label=gene),
size=3, vjust=1, hjust=1) +
xlab(percentage[1]) + ylab(percentage[2]) +
theme_minimal() +
scale_colour_hue(name = "Condition")
select_cond=c("P_t1_Q11L, P_t1_Q11V_L", "P_t1_Q21L, P_t1_Q21V_L", "P_t2_Q11L,
P_t2_Q11V_L", "P_t2_Q21L, P_t2_Q21V_L", "P_t1_Q11V_L,
P_t2_Q11V_L", "P_t1_Q21V_L, P_t2_Q21V_L", "P_t1_Q11L, P_t2_Q11L",
"P_t1_Q21L, P_t2_Q21L", "P_t1_Q11L, P_t1_Q21L", "P_t1_Q11V_L,
P_t1_Q21V_L", "P_t2_Q11L, P_t2_Q21L", "P_t2_Q11V_L, P_t2_Q21V_L")
select_cond="P_t1_Q11L, P_t1_Q21L"
resultsNames(dds_tomato.deseq) #verification## [1] "Intercept" "condition_P_t1_Q11V_L_vs_P_t1_Q11L"
## [3] "condition_P_t1_Q21L_vs_P_t1_Q11L" "condition_P_t1_Q21V_L_vs_P_t1_Q11L"
## [5] "condition_P_t2_Q11L_vs_P_t1_Q11L" "condition_P_t2_Q11V_L_vs_P_t1_Q11L"
## [7] "condition_P_t2_Q21L_vs_P_t1_Q11L" "condition_P_t2_Q21V_L_vs_P_t1_Q11L"for (i in seq_along(select_cond)) {
# Séparer les deux IDs par la virgule
ids <- strsplit(select_cond[i], ",\\s*")[[1]]
ID1 <- ids[1]
ID2 <- ids[2]
res.F <- results(dds_tomato.deseq,contrast = c("condition", ID1, ID2))
res.F$padj <- p.adjust(res.F$pvalue, method = "fdr")
#the padj is by FDR that is less restricted then bonfferoni(BH)
res.F <- res.F[order(res.F$padj), ]
sig_genes.res.F <- row.names(res.F)[which(abs(res.F$padj) < 0.05)]
#catch significant genes between the plants
file_name= paste0("rquantif/Plant/DESeq2_Results_res.P_",
ID1, "_VS_", ID2, ".txt")
# write.csv(res.F, file_name)
# if (length(sig_genes.res.F) > 0){
# write.csv(res.F[sig_genes.res.F,], file_name)
# }
# Ajouter une colonne pour log2FC et -log10(padj)
res.F$log2FoldChange[is.na(res.F$log2FoldChange)] <- 0
res.F$padj[is.na(res.F$padj)] <- 1
res.F$negLogP <- -log10(res.F$padj)
# Ajouter une colonne de statut
res.F$status <- "Non significatif"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange > 0] <- "Sur-exprimé"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange < 0] <- "Sous-exprimé"
# Définir des couleurs accessibles (daltonien-friendly)
colors <- c(
"Sur-exprimé" = "#D55E00", # orange
"Sous-exprimé" = "#0072B2", # bleu
"Non significatif" = "gray70"
)
# Tracer le volcano plot
g <- ggplot(res.F, aes(x = log2FoldChange, y = negLogP, color = status)) +
geom_point(alpha = 0.8, size = 1.5) +
scale_color_manual(values = colors) +
geom_vline(xintercept = 0, color = '#a2a2a2',
alpha=0.7, linewidth = 0.2) +
theme_light() +
labs(title = paste(ID1, "vs", ID2),
x = "log2(Fold Change)", y = "-log10(p-adj)")
print(g)
# ggsave(paste("rquantif/Plant/DESeq2_Results_res.P_", ID1, '_', ID2, '.pdf'),
# plot = g)
}
vsd <- varianceStabilizingTransformation(dds_virus, blind = FALSE)## using 'avgTxLength' from assays(dds), correcting for library size## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.## Warning in lfproc(x, y, weights = weights, cens = cens, base = base, geth =
## geth, : Estimated rdf < 1.0; not estimating variancerld <- rlog(dds_virus, blind=FALSE)## using 'avgTxLength' from assays(dds), correcting for library size
## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.## Warning in lfproc(x, y, weights = weights, cens = cens, base = base, geth =
## geth, : Estimated rdf < 1.0; not estimating variancehead(assay(vsd), 3)## P4L P5L P6L P10L P11L
## lcl|NC_004005.1_cds_NP_658991.1_1 11.64901 10.47116 11.72816 11.73527 10.55861
## lcl|NC_004005.1_cds_NP_658992.1_2 12.93963 12.01717 12.93963 12.93963 12.46655
## lcl|NC_004005.1_cds_NP_658993.1_3 10.63179 10.60390 10.54038 10.41963 10.60390
## P12L P16L P17L P18L P22L
## lcl|NC_004005.1_cds_NP_658991.1_1 10.30715 11.80530 11.75777 11.80195 11.73462
## lcl|NC_004005.1_cds_NP_658992.1_2 12.93963 13.33214 13.16227 13.42752 12.93075
## lcl|NC_004005.1_cds_NP_658993.1_3 11.75629 10.50967 10.54269 10.58001 10.52799
## P23L P24L
## lcl|NC_004005.1_cds_NP_658991.1_1 11.78472 11.50757
## lcl|NC_004005.1_cds_NP_658992.1_2 13.30588 12.94142
## lcl|NC_004005.1_cds_NP_658993.1_3 10.57994 10.60390ntd <- normTransform(dds_virus)## using 'avgTxLength' from assays(dds), correcting for library sizecount.plot <- meanSdPlot(assay(dds_virus))$gg## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
ntd.plot <- meanSdPlot(assay(ntd))$gg## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
vsd.plot <- meanSdPlot(assay(vsd))$gg## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
rld.plot <- meanSdPlot(assay(rld))$gg## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
ggarrange(count.plot,ntd.plot,vsd.plot,rld.plot,
labels=c("counts","ntd","vst","rlog"),ncol=2,nrow=2)## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
## Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
## Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).
df <- bind_rows(
as_tibble(assay(ntd)[, 1:2]) %>% mutate(transformation = "ntd"),
as_tibble(assay(vsd)[, 1:2]) %>% mutate(transformation = "vst"),
as_tibble(assay(rld)[, 1:2]) %>% mutate(transformation = "rlog"))
colnames(df)[1:2] <- c("x", "y")
lvls <- c("ntd", "vst", "rlog")
df$transformation <- factor(df$transformation, levels=lvls)
g = ggplot(df, aes(x = x, y = y)) + geom_hex(bins = 80) +
coord_fixed() + facet_grid( . ~ transformation)
print(g)
select <- order(rowMeans(counts(dds_virus.deseq,normalized=TRUE)),
decreasing=TRUE)
df <- as.data.frame(colData(dds_virus.deseq)[,"sample"])
subset_data_ntd <- assay(ntd)[sample(select, size = 1000, replace = TRUE), ]
subset_data_vsd <- assay(vsd)[sample(select, size = 1000, replace = TRUE), ]
subset_data_rld <- assay(rld)[sample(select, size = 1000, replace = TRUE), ]
data_mat_ntd <- subset_data_ntd
data_mat_ntd <- unique(data_mat_ntd) # enlève les doublons exacts
data_mat_ntd <- jitter(data_mat_ntd)
data_mat_vsd <- subset_data_vsd
data_mat_vsd <- unique(data_mat_vsd) # enlève les doublons exacts
data_mat_vsd <- jitter(data_mat_vsd)
data_mat_rld <- subset_data_rld
data_mat_rld <- unique(data_mat_rld) # enlève les doublons exacts
data_mat_rld <- jitter(data_mat_rld)
k_val_ntd <- min(500, nrow(unique(subset_data_ntd)))
k_val_vsd <- min(500, nrow(unique(subset_data_vsd)))
k_val_rld <- min(500, nrow(unique(subset_data_rld)))
wss <- sapply(1:k_val_ntd, function(k) {
kmeans(data_mat_ntd, centers = k, nstart = 10, algorithm = "Lloyd",
iter.max = 1000)$tot.withinss
})
sampleDists <- dist(t(assay(vsd)))
sampleDistMatrix <- as.matrix(sampleDists)
rownames(sampleDistMatrix) <- paste(vsd$condition, vsd$type, sep = "-")
colnames(sampleDistMatrix) <- NULL
colors <- colorRampPalette(rev(brewer.pal(9, "Blues")))(255)
# 1. Heatmap avec ntd
pheatmap(subset_data_ntd,
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = k_val_ntd)
# 2. Heatmap avec vsd
pheatmap(subset_data_vsd,
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = k_val_vsd)
# 3. Heatmap avec rld
pheatmap(subset_data_rld,
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = k_val_rld)
# 4. Heatmap des distances entre échantillons
pheatmap(sampleDistMatrix,
clustering_distance_rows = sampleDists,
clustering_distance_cols = sampleDists,
col = colors)
vst_df1 <- as.data.frame(t(assay(vsd)))
vst_df1$Treatment <- metadata_virus$condition
pca <- prcomp(vst_df1[,1:ncol(vst_df1)-1])
# Effectuer l'analyse PCA
pca_facto <- PCA(vst_df1[,1:ncol(vst_df1)-1], graph = FALSE)
# Préparer un PDF pour sauvegarde
#pdf("rquantif/Plant/PCA_FactoMineR_Virus_results.pdf", width = 10, height = 12)
## 1. Scree plot
print(fviz_screeplot(pca_facto, addlabels = TRUE, ylim = c(0, 70)))
## 2. Représentation des individus
print(fviz_pca_ind(pca_facto, axes = c(1, 2), repel = TRUE))
## 3. Cos2 des individus - Axe 1 & 2 côte à côte
p1 <- fviz_cos2(pca_facto, choice = "ind", axes = 1,
title = "Qualité de représentation (cos2) - Axe 1")
p2 <- fviz_cos2(pca_facto, choice = "ind", axes = 2,
title = "Qualité de représentation (cos2) - Axe 2")
grid.arrange(p1, p2, ncol = 2)
## 4. Contributions des individus - Axe 1 & 2 côte à côte
p3 <- fviz_contrib(pca_facto, choice = "ind", axes = 1,
title = "Contribution des individus - Axe 1")
p4 <- fviz_contrib(pca_facto, choice = "ind", axes = 2,
title = "Contribution des individus - Axe 2")
grid.arrange(p3, p4, ncol = 2)
## 5. Représentation colorée par cos2
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), title = "Individus - Colorés par cos2"))
## 6. Représentation colorée par contribution
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2),
title = "Individus - Colorés par contribution"))
## 7. Variables les plus contributrices (Top 5)
print(fviz_pca_var(pca_facto, col.var = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), repel = TRUE,
select.var = list(contrib = 5),
title = "Variables - Top 5 contributions"))
# 1. Extraire uniquement les données numériques
X <- vst_df1[, 1:(ncol(vst_df1) - 1)]
groupes <- as.factor(vst_df1$Treatment)
# 2. Analyse en composantes principales avec dudi.pca
acp <- dudi.pca(X, scannf = FALSE, nf = 5)
# 3. Analyse entre groupes (between-class analysis)
acp_btw <- ade4:::between(acp, groupes, scannf = FALSE, nf = 5)## Warning in ade4:::between(acp, groupes, scannf = FALSE, nf = 5): To avoid some
## name conflicts, the 'between' function is now deprecated. Please use 'bca'
## instead# 4. Visualisation
s.class(acp_btw$ls, fac = groupes, col = c("steelblue", "tomato", "darkgreen"),
sub = "Projection des individus entre groupes")
# Fermer le PDF
#dev.off()
df_pca <- as.data.frame(pca$x)
df_pca$Treatment <- metadata_virus$condition
head(df_pca)## PC1 PC2 PC3 PC4 PC5 Treatment
## P4L -0.2175420 -0.04102003 0.251588750 -0.05098803 0.023097121 P_t1_Q21V_L
## P5L 1.2623778 0.61943168 0.020078684 -0.02824930 0.042601053 P_t1_Q21V_L
## P6L -0.2797546 -0.01389344 0.438587198 -0.01529059 -0.075378955 P_t1_Q21V_L
## P10L -0.3358726 0.21141546 0.087908989 0.04787067 0.007369528 P_t1_Q11V_L
## P11L 0.9584303 0.35221482 -0.170120181 -0.01678115 -0.128378719 P_t1_Q11V_L
## P12L 1.2963841 -0.95733280 0.003659814 0.04877545 0.033097805 P_t1_Q11V_Lpercentage <- round(pca$sdev^2 / sum(pca$sdev^2) * 100, 2)
percentage <- paste( colnames(df_pca), "(",
paste( as.character(percentage), "%", ")", sep="") )
g = ggplot(df_pca, aes(PC1, PC2, color=Treatment)) + geom_point(size=2) +
xlab(percentage[1]) + ylab(percentage[2]) +
theme(axis.text.x = element_text(family = "Times"),
axis.title.x = element_text(family = "Times", face = "bold"),
axis.text.y = element_text(family = "Times"),
axis.title.y = element_text(family = "Times", face = "bold"),
legend.title = element_text(family = "Times", face = "bold"),
legend.text = element_text(family = "Times")) +
scale_colour_hue(name = "Condition")
print(g)## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
select_cond_virus=c("P_t1_Q11V_L, P_t2_Q11V_L", "P_t1_Q21V_L, P_t2_Q21V_L",
"P_t1_Q11V_L, P_t1_Q21V_L", "P_t2_Q11V_L, P_t2_Q21V_L")
for (i in seq_along(select_cond_virus)) {
# Séparer les deux IDs par la virgule
ids <- strsplit(select_cond_virus[i], ",\\s*")[[1]]
ID1 <- ids[1]
ID2 <- ids[2]
res.F <- results(dds_virus.deseq ,contrast = c("condition", ID1, ID2))
res.F$padj <- p.adjust(res.F$pvalue, method = "fdr")
#the padj is by FDR that is less restricted then bonfferoni(BH)
res.F <- res.F[order(res.F$padj), ]
sig_genes.res.F <- row.names(res.F)[which(abs(res.F$padj) < 0.05)]
#catch significant genes between the plants
file_name= paste0("rquantif/Plant/DESeq2_Results_res.V_",
ID1, "_VS_", ID2, ".txt")
# write.csv(res.F, file_name)
# if (length(sig_genes.res.F) > 0){
# write.csv(res.F[sig_genes.res.F,], file_name)
# }
# Ajouter une colonne pour log2FC et -log10(padj)
res.F$log2FoldChange[is.na(res.F$log2FoldChange)] <- 0
res.F$padj[is.na(res.F$padj)] <- 1
res.F$negLogP <- -log10(res.F$padj)
# Ajouter une colonne de statut
res.F$status <- "Non significatif"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange > 0] <- "Sur-exprimé"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange < 0] <- "Sous-exprimé"
# Définir des couleurs accessibles (daltonien-friendly)
colors <- c(
"Sur-exprimé" = "#D55E00", # orange
"Sous-exprimé" = "#0072B2", # bleu clair
"Non significatif" = "gray70"
)
# Tracer le volcano plot
g <- ggplot(res.F, aes(x = log2FoldChange, y = negLogP, color = status)) +
geom_point(alpha = 0.8, size = 1.5) +
scale_color_manual(values = colors) +
geom_vline(xintercept = 0, color = '#a2a2a2',
alpha=0.7, linewidth = 0.2) +
theme_light() +
labs(title = paste(ID1, "vs", ID2),
x = "log2(Fold Change)", y = "-log10(p-adj)")
print(g)
# ggsave(paste("rquantif/Plant/DESeq2_Results_res.V_", ID1, '_', ID2, '.pdf'),
# plot = g)
}
1.2 Insect
1.2.1 Import des données pour l’analyse Deseq2 sur les échantillons issus des insectes
# Lire la table de metadata (avec sample, condition, chemin des fichiers)
metadata <- read_excel("metadata_coldata.xlsx",
sheet = "Insect_L")
# Lire la correspondance transcript-gène
tx2gene <- read.table("rquantif/Insect/gene_to_transcript.txt", sep=",",
header=FALSE)
tx2gene <- tx2gene[, c(2, 1)]
assoc_orga <- read.table("rquantif/assoc_orga.txt", sep=",", header=FALSE)
# Ajouter une colonne vide pour orga
tx2gene$orga <- NA
# Boucle pour faire les correspondances partiels
for (i in 1:nrow(assoc_orga)) {
pattern <- assoc_orga$V1[i]
orga_value <- assoc_orga$V2[i]
# Chercher les lignes dont transcript_id contient le pattern
match_idx <- grep(pattern, tx2gene$V2)
# Ajouter l'orga correspondante
tx2gene$orga[match_idx] <- orga_value
}
# Vérifier
head(tx2gene)## V2 V1 orga
## 1 lcl|NC_004005.1_cds_NP_658991.1_1 lcl|NC_004005.1_cds_NP_658991.1_1 TYLCV
## 2 lcl|NC_004005.1_cds_NP_658992.1_2 lcl|NC_004005.1_cds_NP_658992.1_2 TYLCV
## 3 lcl|NC_004005.1_cds_NP_658993.1_3 lcl|NC_004005.1_cds_NP_658993.1_3 TYLCV
## 4 lcl|NC_004005.1_cds_NP_658994.1_4 lcl|NC_004005.1_cds_NP_658994.1_4 TYLCV
## 5 lcl|NC_004005.1_cds_NP_658995.1_5 lcl|NC_004005.1_cds_NP_658995.1_5 TYLCV
## 6 lcl|NC_004005.1_cds_NP_658996.1_6 lcl|NC_004005.1_cds_NP_658996.1_6 TYLCV# Charger les fichiers dans tximport
files <- setNames(metadata$file, metadata$sample)
tx2gene$orga <- trimws(tx2gene$orga)
cytotype =c("Hamiltonella", "Wolbachia", "Rickettsia", "Portiera", "Cardinium",
"Arsenophonus")
tx2gene_bemisia = subset(tx2gene, orga == "Bemisia")
tx2gene_virus = subset(tx2gene, orga == "TYLCV")
tx2gene_cytotype = subset(tx2gene, orga %in% cytotype)
h5closeAll()
txi_bemisia <- tximport(files, type="kallisto", tx2gene = tx2gene_bemisia,
ignoreTxVersion=FALSE)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
## transcripts missing from tx2gene: 6937
## summarizing abundance
## summarizing counts
## summarizing length
## summarizing inferential replicateshead(txi_bemisia$counts)## B1L B2L B3L B4L B5L B6L
## lcl|NC_006279.1_cds_YP_086802.1_24446 114507 112165 121026 37204 113676 151078
## lcl|NC_006279.1_cds_YP_086803.1_24447 221 213 305 62 304 394
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 1 0 0 0 0
## lcl|NC_006279.1_cds_YP_086805.1_24449 0 0 0 0 3 8
## lcl|NC_006279.1_cds_YP_086806.1_24450 31592 27449 39731 12785 31043 42125
## lcl|NC_006279.1_cds_YP_086807.1_24451 38 45 50 24 39 50
## B7L B8L B9L B10L B11L B12L
## lcl|NC_006279.1_cds_YP_086802.1_24446 159440 134268 115555 115838 116060 126121
## lcl|NC_006279.1_cds_YP_086803.1_24447 328 323 242 343 335 302
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 2 3 0 0 0
## lcl|NC_006279.1_cds_YP_086805.1_24449 0 1 2 3 0 3
## lcl|NC_006279.1_cds_YP_086806.1_24450 33145 40829 34005 39736 49424 45166
## lcl|NC_006279.1_cds_YP_086807.1_24451 80 60 52 37 57 64
## B13L B14L B15L B16L B17L B18L
## lcl|NC_006279.1_cds_YP_086802.1_24446 134732 127325 94869 101006 128671 81004
## lcl|NC_006279.1_cds_YP_086803.1_24447 359 409 303 203 353 224
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 0 1 0 1 0
## lcl|NC_006279.1_cds_YP_086805.1_24449 0 0 6 5 0 0
## lcl|NC_006279.1_cds_YP_086806.1_24450 46365 43089 43291 38493 37777 39135
## lcl|NC_006279.1_cds_YP_086807.1_24451 59 67 49 53 50 59
## B19L B20L B21L B22L B23L B24L
## lcl|NC_006279.1_cds_YP_086802.1_24446 131911 86853 136689 123783 118626 144844
## lcl|NC_006279.1_cds_YP_086803.1_24447 376 274 252 271 251 262
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 3 0 0 0 1
## lcl|NC_006279.1_cds_YP_086805.1_24449 3 9 2 3 0 0
## lcl|NC_006279.1_cds_YP_086806.1_24450 44849 42426 26984 27503 30192 29078
## lcl|NC_006279.1_cds_YP_086807.1_24451 63 49 46 47 50 48
## B25L B26L B27L B28L B29L B30L
## lcl|NC_006279.1_cds_YP_086802.1_24446 114377 121210 140690 102575 129635 152923
## lcl|NC_006279.1_cds_YP_086803.1_24447 217 302 270 161 223 297
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 0 0 0 0 1
## lcl|NC_006279.1_cds_YP_086805.1_24449 0 0 0 0 1 1
## lcl|NC_006279.1_cds_YP_086806.1_24450 24546 25044 24553 22472 28591 25869
## lcl|NC_006279.1_cds_YP_086807.1_24451 29 41 50 39 46 40
## B31L B32L B33L B34L B35L B36L
## lcl|NC_006279.1_cds_YP_086802.1_24446 112152 102532 112740 130904 113000 97698
## lcl|NC_006279.1_cds_YP_086803.1_24447 261 263 305 348 401 270
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 0 0 0 0 0
## lcl|NC_006279.1_cds_YP_086805.1_24449 0 1 3 0 2 1
## lcl|NC_006279.1_cds_YP_086806.1_24450 30202 28873 23768 28082 27139 26420
## lcl|NC_006279.1_cds_YP_086807.1_24451 57 48 43 43 55 48
## B37L B38L B39L B40L
## lcl|NC_006279.1_cds_YP_086802.1_24446 101896 98883 134259 153763
## lcl|NC_006279.1_cds_YP_086803.1_24447 243 189 379 417
## lcl|NC_006279.1_cds_YP_086804.1_24448 0 0 0 1
## lcl|NC_006279.1_cds_YP_086805.1_24449 0 2 0 0
## lcl|NC_006279.1_cds_YP_086806.1_24450 28795 30697 31594 31322
## lcl|NC_006279.1_cds_YP_086807.1_24451 47 47 35 52metadata_virus <- metadata[grepl("V", metadata$condition), ]
files_virus <- setNames(metadata_virus$file, metadata_virus$sample)
h5closeAll()
txi_virus <- tximport(files_virus, type="kallisto", tx2gene = tx2gene_virus,
ignoreTxVersion=FALSE)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
## transcripts missing from tx2gene: 31389
## summarizing abundance
## summarizing counts
## summarizing length
## summarizing inferential replicatesverif=txi_virus$counts != 0
head(txi_virus$counts[verif]) #pas de virus ID## numeric(0)h5closeAll()
txi_cytotype <- tximport(files, type="kallisto", tx2gene = tx2gene_cytotype,
ignoreTxVersion=FALSE)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
## transcripts missing from tx2gene: 24516
## summarizing abundance
## summarizing counts
## summarizing length
## summarizing inferential replicateshead(txi_cytotype$counts)## B1L B2L B3L B4L B5L B6L B7L B8L B9L B10L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 126 118 241 179 253 205 401 247 219 251
## lcl|NC_018618.1_cds_PAQ_RS00835_147 217 136 334 222 296 298 497 325 447 362
## lcl|NC_018618.1_cds_PAQ_RS01200_210 19 13 30 34 28 25 59 45 40 26
## lcl|NC_018618.1_cds_PAQ_RS01515_168 13 6 17 4 21 13 20 23 13 9
## lcl|NC_018618.1_cds_PAQ_RS01615_197 33 28 56 34 40 54 72 74 48 87
## lcl|NC_018618.1_cds_PAQ_RS01620_198 46 62 68 29 82 67 144 75 69 113
## B11L B12L B13L B14L B15L B16L B17L B18L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 25 12 10 12 4 7 16 7
## lcl|NC_018618.1_cds_PAQ_RS00835_147 13 18 10 28 23 11 30 16
## lcl|NC_018618.1_cds_PAQ_RS01200_210 3 1 0 0 0 1 1 0
## lcl|NC_018618.1_cds_PAQ_RS01515_168 7 6 5 10 7 6 8 1
## lcl|NC_018618.1_cds_PAQ_RS01615_197 12 4 3 2 2 0 2 0
## lcl|NC_018618.1_cds_PAQ_RS01620_198 3 8 0 1 0 2 5 0
## B19L B20L B21L B22L B23L B24L B25L B26L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 24 8 54 32 50 191 121 172
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6 37 57 58 70 195 181 245
## lcl|NC_018618.1_cds_PAQ_RS01200_210 3 0 5 4 4 12 12 11
## lcl|NC_018618.1_cds_PAQ_RS01515_168 8 17 8 2 22 28 15 35
## lcl|NC_018618.1_cds_PAQ_RS01615_197 6 4 9 21 22 21 18 47
## lcl|NC_018618.1_cds_PAQ_RS01620_198 0 12 13 14 15 56 39 62
## B27L B28L B29L B30L B31L B32L B33L B34L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 374 188 292 326 34 64 37 53
## lcl|NC_018618.1_cds_PAQ_RS00835_147 404 310 331 391 101 96 59 106
## lcl|NC_018618.1_cds_PAQ_RS01200_210 81 18 19 21 7 4 4 10
## lcl|NC_018618.1_cds_PAQ_RS01515_168 31 17 25 32 7 12 21 11
## lcl|NC_018618.1_cds_PAQ_RS01615_197 43 44 47 53 42 11 8 13
## lcl|NC_018618.1_cds_PAQ_RS01620_198 176 85 96 139 22 11 22 36
## B35L B36L B37L B38L B39L B40L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 54 27 42 66 151 154
## lcl|NC_018618.1_cds_PAQ_RS00835_147 49 66 93 134 299 240
## lcl|NC_018618.1_cds_PAQ_RS01200_210 6 0 6 5 12 11
## lcl|NC_018618.1_cds_PAQ_RS01515_168 12 18 34 10 28 23
## lcl|NC_018618.1_cds_PAQ_RS01615_197 16 7 17 19 40 42
## lcl|NC_018618.1_cds_PAQ_RS01620_198 15 19 28 29 53 831.2.2 Formalisations des données
#Tomate
dds_bemisia <- DESeqDataSetFromTximport(txi_bemisia, colData=metadata,
design=~condition)## Warning in DESeqDataSet(se, design = design, ignoreRank): some variables in
## design formula are characters, converting to factors## using counts and average transcript lengths from tximportdds_bemisia <- dds_bemisia[ rowSums(counts(dds_bemisia)) > 10, ]
#Keep only genes with at least 10 count
dds_bemisia.deseq.para <- DESeq(dds_bemisia,fitType = "parametric")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.## final dispersion estimates## fitting model and testingresidual.para <- log(mcols(dds_bemisia.deseq.para)$dispGeneEst) -
log(mcols(dds_bemisia.deseq.para)$dispFit)
median(abs(residual.para))## [1] 1.054587plotDispEsts(dds_bemisia.deseq.para)
dds_bemisia.deseq.local <- DESeq(dds_bemisia,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.local <- log(mcols(dds_bemisia.deseq.local)$dispGeneEst) -
log(mcols(dds_bemisia.deseq.local)$dispFit)
median(abs(residual.local))## [1] 1.054587plotDispEsts(dds_bemisia.deseq.local)
dds_bemisia.deseq.mean <- DESeq(dds_bemisia,fitType = "mean")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.mean <- log(mcols(dds_bemisia.deseq.mean)$dispGeneEst) -
log(mcols(dds_bemisia.deseq.mean)$dispFit)
median(abs(residual.mean))## [1] 4.641961plotDispEsts(dds_bemisia.deseq.mean)
dds_bemisia.deseq <- DESeq(dds_bemisia,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingdds_bemisia.deseq.counts <- round(counts(dds_bemisia.deseq,normalized=TRUE))
#write.csv(dds_bemisia.deseq.counts,
# "rquantif/Insect/dds_bemisia_deseq_counts_hisat2.txt")
#cytotype
dds_cytotype <- DESeqDataSetFromTximport(txi_cytotype, colData=metadata,
design=~condition)## Warning in DESeqDataSet(se, design = design, ignoreRank): some variables in
## design formula are characters, converting to factors## using counts and average transcript lengths from tximportdds_cytotype <- dds_cytotype[ rowSums(counts(dds_cytotype)) > 10, ]
#Keep only genes with at least 10 count
dds_cytotype$condition <- droplevels(dds_cytotype$condition)
dds_cytotype.deseq.para <- DESeq(dds_cytotype, fitType = "parametric")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.## final dispersion estimates## fitting model and testingresidual.para <- log(mcols(dds_cytotype.deseq.para)$dispGeneEst) -
log(mcols(dds_cytotype.deseq.para)$dispFit)
median(abs(residual.para))## [1] 0.6503324plotDispEsts(dds_cytotype.deseq.para)
dds_cytotype.deseq.local <- DESeq(dds_cytotype,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.local <- log(mcols(dds_cytotype.deseq.local)$dispGeneEst) -
log(mcols(dds_cytotype.deseq.local)$dispFit)
median(abs(residual.local))## [1] 0.6503324plotDispEsts(dds_cytotype.deseq.local)
dds_cytotype.deseq.mean <- DESeq(dds_cytotype,fitType = "mean")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingresidual.mean <- log(mcols(dds_cytotype.deseq.mean)$dispGeneEst) -
log(mcols(dds_cytotype.deseq.mean)$dispFit)
median(abs(residual.mean))## [1] 4.073161plotDispEsts(dds_cytotype.deseq.mean)
dds_cytotype.deseq <- DESeq(dds_cytotype,fitType = "local")## estimating size factors## using 'avgTxLength' from assays(dds), correcting for library size## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingdds_cytotype.deseq.counts <- round(counts(dds_cytotype.deseq,normalized=TRUE))
#write.csv(dds_cytotype.deseq.counts,
# "rquantif/Insect/dds_cytotype_deseq_counts_hisat2.txt")1.2.3 Tests et représentations graphiques
vsd <- varianceStabilizingTransformation(dds_bemisia, blind = FALSE)## using 'avgTxLength' from assays(dds), correcting for library size## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.rld <- rlog(dds_bemisia, blind=FALSE)## rlog() may take a few minutes with 30 or more samples,
## vst() is a much faster transformation## using 'avgTxLength' from assays(dds), correcting for library size## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.head(assay(vsd), 3)## B1L B2L B3L B4L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.941846 17.118678 16.683228 15.247989
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.615270 8.704093 8.676746 7.851619
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.353408 7.274131 7.274131
## B5L B6L B7L B8L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.885229 17.102543 17.187546 16.979308
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.853551 8.979451 8.811217 8.822157
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.274131 7.274131 7.371332
## B9L B10L B11L B12L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.679205 16.752761 16.756295 16.986432
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.523509 8.854137 8.833905 8.815047
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.388140 7.274131 7.274131 7.274131
## B13L B14L B15L B16L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.863746 16.924688 16.416272 16.602616
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.833321 9.048018 8.706069 8.458048
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.274131 7.340384 7.274131
## B17L B18L B19L B20L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.807159 16.360720 17.072427 16.468104
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.825435 8.553817 9.032587 8.722351
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.341766 7.274131 7.274131 7.394502
## B21L B22L B23L B24L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.868506 16.697757 16.797784 16.981177
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.539820 8.570163 8.606861 8.586812
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.274131 7.274131 7.339801
## B25L B26L B27L B28L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.633542 16.780078 17.010947 16.704975
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.436662 8.728692 8.658573 8.343867
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.274131 7.274131 7.274131
## B29L B30L B31L B32L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.847342 16.979081 16.586589 16.526562
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.481850 8.643622 8.561243 8.599278
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.339549 7.274131 7.274131
## B33L B34L B35L B36L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.971020 16.979765 16.784877 16.368846
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.926320 8.914770 9.039495 8.563703
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.274131 7.274131 7.274131
## B37L B38L B39L B40L
## lcl|NC_006279.1_cds_YP_086802.1_24446 16.402700 16.343102 16.741629 16.964754
## lcl|NC_006279.1_cds_YP_086803.1_24447 8.475403 8.298439 8.812452 8.923078
## lcl|NC_006279.1_cds_YP_086804.1_24448 7.274131 7.274131 7.274131 7.339355ntd <- normTransform(dds_bemisia)## using 'avgTxLength' from assays(dds), correcting for library sizecount.plot <- meanSdPlot(assay(dds_bemisia))$gg
ntd.plot <- meanSdPlot(assay(ntd))$gg
vsd.plot <- meanSdPlot(assay(vsd))$gg
rld.plot <- meanSdPlot(assay(rld))$gg
ggarrange(count.plot,ntd.plot,vsd.plot,rld.plot,
labels=c("counts","ntd","vst","rlog"),ncol=2,nrow=2)
df <- bind_rows(
as_tibble(assay(ntd)[, 1:2]) %>% mutate(transformation = "ntd"),
as_tibble(assay(vsd)[, 1:2]) %>% mutate(transformation = "vst"),
as_tibble(assay(rld)[, 1:2]) %>% mutate(transformation = "rlog"))
colnames(df)[1:2] <- c("x", "y")
lvls <- c("ntd", "vst", "rlog")
df$transformation <- factor(df$transformation, levels=lvls)
g = ggplot(df, aes(x = x, y = y)) + geom_hex(bins = 80) +
coord_fixed() + facet_grid( . ~ transformation)
print(g)
select <- order(rowMeans(counts(dds_bemisia.deseq,normalized=TRUE)),
decreasing=TRUE)
df <- as.data.frame(colData(dds_bemisia.deseq)[,"sample"])
wss <- sapply(1:10, function(k) {
kmeans(assay(ntd)[select, ], centers = k, nstart = 10, algorithm = "Lloyd",
iter.max = 1000)$tot.withinss
})
# 1. Heatmap avec ntd
pheatmap(assay(ntd)[select,],
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = 500)
# 2. Heatmap avec vsd
pheatmap(assay(vsd)[select,],
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = 500)
# 3. Heatmap avec rld
pheatmap(assay(rld)[select,],
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = 500)
# 4. Heatmap des distances entre échantillons
sampleDists <- dist(t(assay(vsd)))
sampleDistMatrix <- as.matrix(sampleDists)
rownames(sampleDistMatrix) <- paste(vsd$condition, vsd$type, sep = "-")
colnames(sampleDistMatrix) <- NULL
colors <- colorRampPalette(rev(brewer.pal(9, "Blues")))(255)
pheatmap(sampleDistMatrix,
clustering_distance_rows = sampleDists,
clustering_distance_cols = sampleDists,
col = colors)
vst_df1 <- as.data.frame(t(assay(vsd)))
vst_df1$Treatment <- metadata$condition
pca <- prcomp(vst_df1[,1:ncol(vst_df1)-1])
# Effectuer l'analyse PCA
pca_facto <- PCA(vst_df1[,1:ncol(vst_df1)-1], graph = FALSE)
# Préparer un PDF pour sauvegarde
#pdf("rquantif/Insect/PCA_FactoMineR_Bemisia_results.pdf", width = 10,
# height = 12)
## 1. Scree plot
print(fviz_screeplot(pca_facto, addlabels = TRUE, ylim = c(0, 70)))
## 2. Représentation des individus
print(fviz_pca_ind(pca_facto, axes = c(1, 2), repel = TRUE))
## 3. Cos2 des individus - Axe 1 & 2 côte à côte
p1 <- fviz_cos2(pca_facto, choice = "ind", axes = 1,
title = "Qualité de représentation (cos2) - Axe 1")
p2 <- fviz_cos2(pca_facto, choice = "ind", axes = 2,
title = "Qualité de représentation (cos2) - Axe 2")
grid.arrange(p1, p2, ncol = 2)
## 4. Contributions des individus - Axe 1 & 2 côte à côte
p3 <- fviz_contrib(pca_facto, choice = "ind", axes = 1,
title = "Contribution des individus - Axe 1")
p4 <- fviz_contrib(pca_facto, choice = "ind", axes = 2,
title = "Contribution des individus - Axe 2")
grid.arrange(p3, p4, ncol = 2)
## 5. Représentation colorée par cos2
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), title = "Individus - Colorés par cos2"))
## 6. Représentation colorée par contribution
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2),
title = "Individus - Colorés par contribution"))
## 7. Variables les plus contributrices (Top 5)
print(fviz_pca_var(pca_facto, col.var = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), repel = TRUE,
select.var = list(contrib = 5),
title = "Variables - Top 5 contributions"))
# 1. Extraire uniquement les données numériques
X <- vst_df1[, 1:(ncol(vst_df1) - 1)]
groupes <- as.factor(vst_df1$Treatment)
# 2. Analyse en composantes principales avec dudi.pca
acp <- dudi.pca(X, scannf = FALSE, nf = 5)
# 3. Analyse entre groupes (between-class analysis)
acp_btw <- ade4:::between(acp, groupes, scannf = FALSE, nf = 5)## Warning in ade4:::between(acp, groupes, scannf = FALSE, nf = 5): To avoid some
## name conflicts, the 'between' function is now deprecated. Please use 'bca'
## instead# 4. Visualisation
s.class(acp_btw$ls, fac = groupes, col = c("steelblue", "tomato", "darkgreen"),
sub = "Projection des individus entre groupes")
# Fermer le PDF
#dev.off()
df_pca <- as.data.frame(pca$x)
df_pca$Treatment <- metadata$condition
head(df_pca)## PC1 PC2 PC3 PC4 PC5 PC6 PC7
## B1L -9.622603 8.372318 6.737333 -6.456848 -4.5302312 0.3506767 -1.7647136
## B2L -29.636426 16.607991 6.834900 16.831572 -3.6745249 6.4070886 3.2067236
## B3L -3.074600 8.406587 6.217534 -5.359011 -5.2199654 5.5855708 -2.6144713
## B4L -17.018172 29.936036 -43.025295 -8.081412 0.9934767 0.1676285 -1.3743044
## B5L 2.007442 4.776853 6.697173 -15.295947 -3.3690963 2.0931569 -0.6045413
## B6L -5.319688 3.588753 6.365667 -16.745114 0.9748201 -2.3033729 1.4273075
## PC8 PC9 PC10 PC11 PC12 PC13
## B1L 2.7178591 -3.8773495 0.1253114 6.6824878 -6.4032795 3.4689407
## B2L -17.5877098 -0.9532186 2.8042817 -0.8407784 -2.9697205 -3.7173066
## B3L 3.9234850 -1.4715399 3.7273625 -0.2779724 -3.5807414 -0.6587047
## B4L -0.1790356 -0.4498469 -0.1634209 -0.2257450 0.5833309 0.1258588
## B5L 0.5068259 0.8023655 4.3615720 0.8418124 0.6674006 -1.2734918
## B6L -2.5098142 2.7211503 -0.6836151 0.7698852 4.7185288 0.8218754
## PC14 PC15 PC16 PC17 PC18 PC19
## B1L 1.7719642 -3.8583507 -5.48144401 12.35935179 0.2284307 -3.9051852
## B2L 4.6811837 1.7428651 1.81360851 1.51111975 0.1132305 1.2936620
## B3L 2.3526782 3.0600301 1.05984369 -1.79731655 -7.2013276 -8.1976235
## B4L 0.1753681 -0.2892047 0.57234046 -0.09164923 0.1480173 -0.2248493
## B5L -0.3004929 3.4128826 0.05580584 -2.75565260 -5.5584517 -0.5662526
## B6L -0.1549251 -1.0318955 -2.21553319 1.02456116 -0.4574689 0.5829403
## PC20 PC21 PC22 PC23 PC24 PC25
## B1L -3.1384856 -5.56399401 4.3615761 1.5615069 2.0116062 0.9619146
## B2L 0.3874994 0.99662672 0.5581961 -0.1719685 -0.3167858 2.1642652
## B3L -0.1790090 0.09762588 -1.8897633 1.9600774 -4.9050765 -5.1804468
## B4L 0.2696366 0.02129920 0.1195363 0.2910057 0.2349607 -0.1852221
## B5L -2.0883144 6.78569890 -4.3399900 1.3208957 2.7469715 6.4094688
## B6L -1.1047445 2.13684932 -0.4745441 -0.8941080 -7.4351700 5.3435865
## PC26 PC27 PC28 PC29 PC30 PC31
## B1L -3.4389325 -1.9137561 -0.3044816 -0.029958763 -0.05905727 -0.883299690
## B2L -0.5935144 0.3343332 0.5145969 -0.358617912 -0.35927336 -0.028313642
## B3L 5.0910326 7.9512834 -2.7289836 2.670948012 -3.20071461 2.500198696
## B4L 0.1470147 -0.0435218 0.1299864 -0.005501495 0.10360085 -0.001939443
## B5L -3.2497100 -1.4452368 6.2382569 1.319649322 4.42738184 1.826461633
## B6L -0.4495837 -4.1874044 1.7310469 0.506036898 -4.77854552 -4.853435314
## PC32 PC33 PC34 PC35 PC36 PC37
## B1L 2.40604687 0.7587713 0.5320164 -1.26931047 -1.8776706 1.102016029
## B2L 0.24479703 0.1357489 -0.3362142 -0.27099039 0.7251075 0.007766917
## B3L -0.43973811 -1.5806796 1.1873351 -0.19283515 1.6173611 -1.679893801
## B4L 0.04431119 0.2053629 0.1408394 -0.02939291 -0.2140555 -0.111152934
## B5L 3.20630581 6.0176623 2.3037523 0.13181247 -1.0159728 0.393453950
## B6L -2.33328934 -7.2270878 1.5133711 -0.04114272 3.5742818 -1.202760470
## PC38 PC39 PC40 Treatment
## B1L 0.56042934 -0.44924226 -6.078659e-15 B_t1_Q21L
## B2L 0.06525671 0.80283563 -3.283058e-14 B_t1_Q21L
## B3L 0.21789691 1.06032219 -6.713336e-14 B_t1_Q21L
## B4L 0.05187198 -0.02639112 -4.415609e-14 B_t1_Q21L
## B5L -0.99207876 -3.08060959 -6.650903e-14 B_t1_Q21L
## B6L -2.88677371 4.71811159 -8.246433e-14 B_t1_Q21V_Lpercentage <- round(pca$sdev^2 / sum(pca$sdev^2) * 100, 2)
percentage <- paste( colnames(df_pca), "(",
paste( as.character(percentage), "%", ")", sep="") )
g = ggplot(df_pca, aes(PC1, PC2, color=Treatment)) + geom_point(size=2) +
xlab(percentage[1]) + ylab(percentage[2]) +
theme(axis.text.x = element_text(family = "Times"),
axis.title.x = element_text(family = "Times", face = "bold"),
axis.text.y = element_text(family = "Times"),
axis.title.y = element_text(family = "Times", face = "bold"),
legend.title = element_text(family = "Times", face = "bold"),
legend.text = element_text(family = "Times")) +
scale_colour_hue(name = "Condition")
print(g)## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
select_cond=c("B_t1_Q11L, B_t1_Q11V_L", "B_t1_Q21L, B_t1_Q21V_L", "B_t2_Q11L,
B_t2_Q11V_L", "B_t2_Q21L, B_t2_Q21V_L", "B_t1_Q11V_L,
B_t2_Q11V_L", "B_t1_Q21V_L, B_t2_Q21V_L", "B_t1_Q11L, B_t2_Q11L",
"B_t1_Q21L, B_t2_Q21L", "B_t1_Q11L, B_t1_Q21L", "B_t1_Q11V_L,
B_t1_Q21V_L", "B_t2_Q11L, B_t2_Q21L", "B_t2_Q11V_L, B_t2_Q21V_L")
select_cond="B_t1_Q11L, B_t1_Q21L"
#"B_t1_Q11L, B_t2_Q11L"
resultsNames(dds_bemisia.deseq) #verification## [1] "Intercept" "condition_B_t1_Q11V_L_vs_B_t1_Q11L"
## [3] "condition_B_t1_Q21L_vs_B_t1_Q11L" "condition_B_t1_Q21V_L_vs_B_t1_Q11L"
## [5] "condition_B_t2_Q11L_vs_B_t1_Q11L" "condition_B_t2_Q11V_L_vs_B_t1_Q11L"
## [7] "condition_B_t2_Q21L_vs_B_t1_Q11L" "condition_B_t2_Q21V_L_vs_B_t1_Q11L"for (i in seq_along(select_cond)) {
# Séparer les deux IDs par la virgule
ids <- strsplit(select_cond[i], ",\\s*")[[1]]
ID1 <- ids[1]
ID2 <- ids[2]
res.F <- results(dds_bemisia.deseq,contrast = c("condition", ID1, ID2))
res.F$padj <- p.adjust(res.F$pvalue, method = "fdr")
#the padj is by FDR that is less restricted then bonfferoni(BH)
res.F <- res.F[order(res.F$padj), ]
sig_genes.res.F <- row.names(res.F)[which(abs(res.F$padj) < 0.05)]
#catch significant genes between the Insects
file_name= paste0("rquantif/Insect/DESeq2_Results_res.I_",
ID1, "_VS_", ID2, ".txt")
# write.csv(res.F, file_name)
# if (length(sig_genes.res.F) > 0){
# write.csv(res.F[sig_genes.res.F,], file_name)
# }
# Ajouter une colonne pour log2FC et -log10(padj)
res.F$log2FoldChange[is.na(res.F$log2FoldChange)] <- 0
res.F$padj[is.na(res.F$padj)] <- 1
res.F$negLogP <- -log10(res.F$padj)
# Ajouter une colonne de statut
res.F$status <- "Non significatif"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange > 0] <- "Sur-exprimé"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange < 0] <- "Sous-exprimé"
# Définir des couleurs accessibles (daltonien-friendly)
colors <- c(
"Sur-exprimé" = "#D55E00", # orange
"Sous-exprimé" = "#0072B2", # bleu clair
"Non significatif" = "gray70"
)
# Tracer le volcano plot
g <- ggplot(res.F, aes(x = log2FoldChange, y = negLogP, color = status)) +
geom_point(alpha = 0.8, size = 1.5) +
scale_color_manual(values = colors) +
geom_vline(xintercept = 0, color = '#a2a2a2',
alpha=0.7, linewidth = 0.2) +
theme_light() +
labs(title = paste(ID1, "vs", ID2),
x = "log2(Fold Change)", y = "-log10(p-adj)")
print(g)
# ggsave(paste("rquantif/Insect/DESeq2_Results_res.B_", ID1, '_', ID2, '.pdf'),
# plot = g)
}
vsd <- varianceStabilizingTransformation(dds_cytotype, blind = FALSE)## using 'avgTxLength' from assays(dds), correcting for library size## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.rld <- rlog(dds_cytotype, blind=FALSE)## rlog() may take a few minutes with 30 or more samples,
## vst() is a much faster transformation## using 'avgTxLength' from assays(dds), correcting for library size## -- note: fitType='parametric', but the dispersion trend was not well captured by the
## function: y = a/x + b, and a local regression fit was automatically substituted.
## specify fitType='local' or 'mean' to avoid this message next time.head(assay(vsd), 3)## B1L B2L B3L B4L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 6.287347 6.392612 6.489676 7.120189
## lcl|NC_018618.1_cds_PAQ_RS00835_147 7.103016 6.598571 6.984696 7.464447
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.386003 4.263904 4.358143 4.920503
## B5L B6L B7L B8L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 6.739285 6.407870 6.644427 6.422697
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.982641 6.971050 6.972432 6.831850
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.388178 4.313165 4.553925 4.596858
## B9L B10L B11L B12L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 6.199389 6.414331 6.348956 5.578151
## lcl|NC_018618.1_cds_PAQ_RS00835_147 7.272238 6.964890 5.519293 6.079140
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.498927 4.226584 4.303566 3.873117
## B13L B14L B15L B16L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 5.512648 5.704905 4.687949 4.888984
## lcl|NC_018618.1_cds_PAQ_RS00835_147 5.512756 6.873190 6.668866 5.322777
## lcl|NC_018618.1_cds_PAQ_RS01200_210 3.465082 3.465082 3.465082 3.833159
## B17L B18L B19L B20L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 5.607340 5.131293 6.746970 5.017174
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.423354 6.079092 5.042749 6.926972
## lcl|NC_018618.1_cds_PAQ_RS01200_210 3.825558 3.465082 4.484604 3.465082
## B21L B22L B23L B24L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 6.068495 5.393669 5.831179 6.573595
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.140549 6.110859 6.274028 6.603973
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.069937 3.949903 3.932803 4.040256
## B25L B26L B27L B28L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 6.262885 6.166653 6.600732 6.224885
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.853961 6.673648 6.717867 6.961723
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.156300 3.940989 4.847054 4.121710
## B29L B30L B31L B32L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 6.569086 6.560886 5.361408 6.051598
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.757587 6.835288 6.778218 6.621534
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.063468 4.078924 4.156488 3.888593
## B33L B34L B35L B36L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 5.892676 5.903351 6.170229 5.268310
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.530845 6.885144 6.040360 6.359459
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.106723 4.389276 4.162538 3.465082
## B37L B38L B39L B40L
## lcl|NC_018618.1_cds_PAQ_RS00660_119 5.587798 6.002338 6.113905 6.322908
## lcl|NC_018618.1_cds_PAQ_RS00835_147 6.641188 7.026771 7.124702 6.986538
## lcl|NC_018618.1_cds_PAQ_RS01200_210 4.090904 3.951401 4.019345 4.048328ntd <- normTransform(dds_cytotype)## using 'avgTxLength' from assays(dds), correcting for library sizecount.plot <- meanSdPlot(assay(dds_cytotype))$gg
ntd.plot <- meanSdPlot(assay(ntd))$gg
vsd.plot <- meanSdPlot(assay(vsd))$gg
rld.plot <- meanSdPlot(assay(rld))$gg
ggarrange(count.plot,ntd.plot,vsd.plot,rld.plot,
labels=c("counts","ntd","vst","rlog"),ncol=2,nrow=2)
df <- bind_rows(
as_tibble(assay(ntd)[, 1:2]) %>% mutate(transformation = "ntd"),
as_tibble(assay(vsd)[, 1:2]) %>% mutate(transformation = "vst"),
as_tibble(assay(rld)[, 1:2]) %>% mutate(transformation = "rlog"))
colnames(df)[1:2] <- c("x", "y")
lvls <- c("ntd", "vst", "rlog")
df$transformation <- factor(df$transformation, levels=lvls)
g = ggplot(df, aes(x = x, y = y)) + geom_hex(bins = 80) +
coord_fixed() + facet_grid( . ~ transformation)
print(g)
select <- order(rowMeans(counts(dds_cytotype.deseq,normalized=TRUE)),
decreasing=TRUE)
df <- as.data.frame(colData(dds_cytotype.deseq)[,"sample"])
subset_data_ntd <- assay(ntd)[sample(select, size = 1000, replace = TRUE), ]
subset_data_vsd <- assay(vsd)[sample(select, size = 1000, replace = TRUE), ]
subset_data_rld <- assay(rld)[sample(select, size = 1000, replace = TRUE), ]
data_mat_ntd <- subset_data_ntd
data_mat_ntd <- unique(data_mat_ntd) # enlève les doublons exacts
data_mat_ntd <- jitter(data_mat_ntd)
data_mat_vsd <- subset_data_vsd
data_mat_vsd <- unique(data_mat_vsd) # enlève les doublons exacts
data_mat_vsd <- jitter(data_mat_vsd)
data_mat_rld <- subset_data_rld
data_mat_rld <- unique(data_mat_rld) # enlève les doublons exacts
data_mat_rld <- jitter(data_mat_rld)
k_val_ntd <- min(500, nrow(unique(subset_data_ntd)))
k_val_vsd <- min(500, nrow(unique(subset_data_vsd)))
k_val_rld <- min(500, nrow(unique(subset_data_rld)))
wss <- sapply(1:k_val_ntd, function(k) {
kmeans(data_mat_ntd, centers = k, nstart = 10, algorithm = "Lloyd",
iter.max = 1000)$tot.withinss
})## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleur
## Warning: classe vide : essayez un jeu de centres meilleursampleDists <- dist(t(assay(vsd)))
sampleDistMatrix <- as.matrix(sampleDists)
rownames(sampleDistMatrix) <- paste(vsd$condition, vsd$type, sep = "-")
colnames(sampleDistMatrix) <- NULL
colors <- colorRampPalette(rev(brewer.pal(9, "Blues")))(255)
# 1. Heatmap avec ntd
pheatmap(subset_data_ntd,
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = k_val_ntd)
# 2. Heatmap avec vsd
pheatmap(subset_data_vsd,
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = k_val_vsd)
# 3. Heatmap avec rld
pheatmap(subset_data_rld,
cluster_rows = TRUE, show_rownames = FALSE,
cluster_cols = TRUE, show_colnames = FALSE,
kmeans_k = k_val_rld)
# 4. Heatmap des distances entre échantillons
pheatmap(sampleDistMatrix,
clustering_distance_rows = sampleDists,
clustering_distance_cols = sampleDists,
col = colors)
vst_df1 <- as.data.frame(t(assay(vsd)))
vst_df1$Treatment <- metadata$condition
pca <- prcomp(vst_df1[,1:ncol(vst_df1)-1])
# Préparer un PDF pour sauvegarde
#pdf("rquantif/Insect/PCA_FactoMineR_Cytotype_results.pdf", width = 10,
# height = 12)
## 1. Scree plot
print(fviz_screeplot(pca_facto, addlabels = TRUE, ylim = c(0, 70)))
## 2. Représentation des individus
print(fviz_pca_ind(pca_facto, axes = c(1, 2), repel = TRUE))
## 3. Cos2 des individus - Axe 1 & 2 côte à côte
p1 <- fviz_cos2(pca_facto, choice = "ind", axes = 1,
title = "Qualité de représentation (cos2) - Axe 1")
p2 <- fviz_cos2(pca_facto, choice = "ind", axes = 2,
title = "Qualité de représentation (cos2) - Axe 2")
grid.arrange(p1, p2, ncol = 2)
## 4. Contributions des individus - Axe 1 & 2 côte à côte
p3 <- fviz_contrib(pca_facto, choice = "ind", axes = 1,
title = "Contribution des individus - Axe 1")
p4 <- fviz_contrib(pca_facto, choice = "ind", axes = 2,
title = "Contribution des individus - Axe 2")
grid.arrange(p3, p4, ncol = 2)
## 5. Représentation colorée par cos2
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), title = "Individus - Colorés par cos2"))
## 6. Représentation colorée par contribution
print(fviz_pca_ind(pca_facto, repel = TRUE, col.ind = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2),
title = "Individus - Colorés par contribution"))
## 7. Variables les plus contributrices (Top 5)
print(fviz_pca_var(pca_facto, col.var = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
axes = c(1, 2), repel = TRUE,
select.var = list(contrib = 5),
title = "Variables - Top 5 contributions"))
# 1. Extraire uniquement les données numériques
X <- vst_df1[, 1:(ncol(vst_df1) - 1)]
groupes <- as.factor(vst_df1$Treatment)
# 2. Analyse en composantes principales avec dudi.pca
acp <- dudi.pca(X, scannf = FALSE, nf = 5)
# 3. Analyse entre groupes (between-class analysis)
acp_btw <- ade4:::between(acp, groupes, scannf = FALSE, nf = 5)## Warning in ade4:::between(acp, groupes, scannf = FALSE, nf = 5): To avoid some
## name conflicts, the 'between' function is now deprecated. Please use 'bca'
## instead# 4. Visualisation
s.class(acp_btw$ls, fac = groupes, col = c("steelblue", "tomato", "darkgreen"),
sub = "Projection des individus entre groupes")
# Fermer le PDF
#dev.off()
df_pca <- as.data.frame(pca$x)
df_pca$Treatment <- metadata$condition
head(df_pca)## PC1 PC2 PC3 PC4 PC5 PC6
## B1L -4.286879 -0.621567454 0.02980711 -0.3918758 0.6728402 -0.53579207
## B2L -3.079178 0.003234504 -0.48040128 -0.2760292 0.5157141 -0.40830429
## B3L -6.521770 -1.663057933 -0.37150399 -0.6249179 1.1370346 0.31549496
## B4L -6.773662 -2.627761352 -1.01786778 -1.0667494 4.2329095 -1.25127812
## B5L -6.589906 -0.179042366 -0.13681845 -0.3737296 1.1848833 -0.00201096
## B6L -6.621218 -0.847945685 -0.50144171 -0.3358337 1.0838811 -0.07200709
## PC7 PC8 PC9 PC10 PC11 PC12
## B1L 0.6193909 -0.1015177 0.31364931 -1.4064133 0.2494543 0.36998920
## B2L 1.5141679 0.3899437 0.15180587 -0.8664044 0.4296221 -0.72320237
## B3L 1.0379321 -0.3899539 0.04533722 -1.0854331 -0.9664986 -0.03354986
## B4L 0.1701296 -1.8294168 0.73471968 5.6840085 3.1451596 -1.67704916
## B5L 1.2624603 -0.1361278 0.11873572 -1.2641458 -0.3338287 0.06646135
## B6L 1.0978624 -0.1181670 0.28887858 -1.1717623 -0.6240227 -0.05154107
## PC13 PC14 PC15 PC16 PC17 PC18
## B1L -0.32230363 0.47742489 -0.40177709 0.2567987 0.7509373 -0.48166735
## B2L -0.06923783 2.43519295 -0.98145064 0.3708906 0.9168041 -0.30599252
## B3L -0.29468039 -0.83936767 -0.34117863 0.2923987 0.3164200 -0.09002289
## B4L -0.22199746 0.12494151 -0.56457478 -0.3012580 -0.4747489 0.00943062
## B5L -0.09885235 0.04152965 0.01785049 0.1288856 0.1749938 -0.16114479
## B6L -0.37967874 -0.63281227 -0.11363636 0.4277944 0.6802721 -0.43675076
## PC19 PC20 PC21 PC22 PC23 PC24
## B1L -0.2273164 -0.12395850 -0.09747282 -0.8991981 0.05885335 0.8374187
## B2L -1.7203745 2.11534567 -0.40575211 0.8245344 -0.52242805 -1.3532086
## B3L -0.2306214 -0.48365751 0.01132052 -0.1493762 0.75425900 0.1866568
## B4L -0.0219422 -0.07391869 0.06916941 0.1686847 -0.03946347 0.2462018
## B5L 0.1463607 -0.51100339 0.18702124 -0.2785667 0.31840862 0.5556325
## B6L 0.2120679 -0.23522690 0.60149661 -0.1535121 0.18611420 0.3943821
## PC25 PC26 PC27 PC28 PC29 PC30
## B1L 0.43764618 1.72803120 -1.32199419 -0.3306104 0.186083892 1.13368476
## B2L -0.83597738 -0.74097853 -1.25518585 0.4007908 0.006210601 -0.01279870
## B3L -0.38413382 -0.59003976 0.01613758 -0.8888158 1.310776015 -0.05191703
## B4L 0.48535392 0.02156591 -0.14269379 -0.1418867 -0.143653880 0.01662797
## B5L 0.06535619 -0.03429883 -0.06948546 0.4586843 0.029649364 0.20310952
## B6L 0.25360590 -0.25478655 0.37642665 1.1108484 -0.483196934 0.89746372
## PC31 PC32 PC33 PC34 PC35 PC36
## B1L 0.86460492 -0.94583370 -0.25886647 -0.18284268 -0.27365076 -0.73574050
## B2L 0.20403218 0.10291826 0.29341570 -0.03872676 0.05078148 0.23649435
## B3L -0.31993694 0.43325344 1.22282705 0.35712194 -0.93766684 -0.05842936
## B4L -0.03879686 0.05118106 0.04778272 0.07751079 -0.04844731 0.02076011
## B5L 1.01081912 1.40571765 -1.34378000 0.28307851 -0.35953529 1.14307037
## B6L -0.88593544 -0.45678064 0.78174690 -0.47777716 0.20167243 0.54374282
## PC37 PC38 PC39 PC40 Treatment
## B1L 0.08816968 0.024283480 0.03450363 4.951822e-15 B_t1_Q21L
## B2L -0.03288484 0.046098353 -0.10340659 4.392591e-15 B_t1_Q21L
## B3L 0.65698135 -0.167108115 0.62987640 4.032202e-15 B_t1_Q21L
## B4L -0.04570916 -0.008746499 0.02989627 4.224973e-15 B_t1_Q21L
## B5L -0.24608081 0.054735067 0.25142840 4.781765e-15 B_t1_Q21L
## B6L -1.03034398 -0.847823064 0.08995165 4.488760e-15 B_t1_Q21V_Lpercentage <- round(pca$sdev^2 / sum(pca$sdev^2) * 100, 2)
percentage <- paste( colnames(df_pca), "(",
paste( as.character(percentage), "%", ")", sep="") )
g = ggplot(df_pca, aes(PC1, PC2, color=Treatment)) + geom_point(size=2) +
xlab(percentage[1]) + ylab(percentage[2]) +
theme(axis.text.x = element_text(family = "Times"),
axis.title.x = element_text(family = "Times", face = "bold"),
axis.text.y = element_text(family = "Times"),
axis.title.y = element_text(family = "Times", face = "bold"),
legend.title = element_text(family = "Times", face = "bold"),
legend.text = element_text(family = "Times")) +
scale_colour_hue(name = "Condition")
print(g)## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## famille de police introuvable dans la base de données des polices Windows
select_cond=c("B_t1_Q11L, B_t1_Q11V_L", "B_t1_Q21L, B_t1_Q21V_L", "B_t2_Q11L,
B_t2_Q11V_L", "B_t2_Q21L, B_t2_Q21V_L", "B_t1_Q11V_L,
B_t2_Q11V_L", "B_t1_Q21V_L, B_t2_Q21V_L", "B_t1_Q11L, B_t2_Q11L",
"B_t1_Q21L, B_t2_Q21L", "B_t1_Q11L, B_t1_Q21L", "B_t1_Q11V_L,
B_t1_Q21V_L", "B_t2_Q11L, B_t2_Q21L", "B_t2_Q11V_L, B_t2_Q21V_L")
for (i in seq_along(select_cond)) {
# Séparer les deux IDs par la virgule
ids <- strsplit(select_cond[i], ",\\s*")[[1]]
ID1 <- ids[1]
ID2 <- ids[2]
res.F <- results(dds_cytotype.deseq ,contrast = c("condition", ID1, ID2))
res.F$padj <- p.adjust(res.F$pvalue, method = "fdr")
#the padj is by FDR that is less restricted then bonfferoni(BH)
res.F <- res.F[order(res.F$padj), ]
sig_genes.res.F <- row.names(res.F)[which(abs(res.F$padj) < 0.05)]
#catch significant genes between the Insects
file_name= paste0("rquantif/Insect/DESeq2_Results_res.F.C_",
ID1, "_VS_", ID2, ".txt")
write.csv(res.F, file_name)
volcano_name= paste0("volcano_C_", ID1, "_VS_", ID2, ".pdf")
if (length(sig_genes.res.F) > 0){
write.csv(res.F[sig_genes.res.F,], file_name)
}
# Ajouter une colonne pour log2FC et -log10(padj)
res.F$log2FoldChange[is.na(res.F$log2FoldChange)] <- 0
res.F$padj[is.na(res.F$padj)] <- 1
res.F$negLogP <- -log10(res.F$padj)
# Ajouter une colonne de statut
res.F$status <- "Non significatif"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange > 0] <- "Sur-exprimé"
res.F$status[res.F$padj < 0.05 & res.F$log2FoldChange < 0] <- "Sous-exprimé"
# Définir des couleurs accessibles (daltonien-friendly)
colors <- c(
"Sur-exprimé" = "#D55E00", # orange
"Sous-exprimé" = "#0072B2", # bleu clair
"Non significatif" = "gray70"
)
# Tracer le volcano plot
g <- ggplot(res.F, aes(x = log2FoldChange, y = negLogP, color = status)) +
geom_point(alpha = 0.8, size = 1.5) +
scale_color_manual(values = colors) +
geom_vline(xintercept = 0, color = '#a2a2a2',
alpha=0.7, linewidth = 0.2) +
theme_light() +
labs(title = paste(ID1, "vs", ID2),
x = "log2(Fold Change)", y = "-log10(p-adj)")
print(g)
# ggsave(paste("rquantif/Insect/DESeq2_Results_res.C_", ID1, '_', ID2, '.pdf'),
# plot = g)
}
2 TopGO analysis
2.1 Plant
2.1.1 Import des données pour l’analyse TopGO sur les échantillons issus des plantes
# Annotations GO (InterProScan)
interproscan <- read.delim('TopGO/Plant/plant_GO_sorted.txt',
header = FALSE, sep = '\t')
head(interproscan)## V1 V2
## 1 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338_orf235147 GO:0003677
## 2 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338_orf235147 GO:0003824
## 3 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338_orf235147 GO:0004518
## 4 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338_orf235147 GO:0016788
## 5 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338_orf739763 GO:0003677
## 6 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338_orf739763 GO:0003824interproscan$V1 <- vapply(interproscan$V1,
function(x) gsub('_orf[0-9]+', '', x), character(1))
#take out the orf part
interproscan <- as.data.frame(interproscan)
head(interproscan)## V1 V2
## 1 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 GO:0003677
## 2 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 GO:0003824
## 3 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 GO:0004518
## 4 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 GO:0016788
## 5 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 GO:0003677
## 6 lcl|CAKKNF020000001.1_cds_CAH0746830.1_16338 GO:0003824# Vérifier la structure des fichiers
if (ncol(interproscan) < 2)
stop('Erreur : Le fichier interproscan semble mal formaté.')
# Définir la liste des conditions d’intérêt
select_cond <- c(
"P_t1_Q11L, P_t1_Q11V_L",
"P_t1_Q21L, P_t1_Q21V_L",
"P_t2_Q11L, P_t2_Q11V_L",
"P_t2_Q21L, P_t2_Q21V_L",
"P_t1_Q11V_L, P_t2_Q11V_L",
"P_t1_Q21V_L, P_t2_Q21V_L",
"P_t1_Q11L, P_t2_Q11L",
"P_t1_Q21L, P_t2_Q21L",
"P_t1_Q11L, P_t1_Q21L",
"P_t1_Q11V_L, P_t1_Q21V_L",
"P_t2_Q11L, P_t2_Q21L",
"P_t2_Q11V_L, P_t2_Q21V_L"
)
# Lire les lignes du fichier contenant les chemins et infos
lines_raw <- readLines("TopGO/Plant/liste_deseq.txt")## Warning in readLines("TopGO/Plant/liste_deseq.txt"): ligne finale incomplète
## trouvée dans 'TopGO/Plant/liste_deseq.txt'# Initialiser une liste de résultats
chemins_trouves <- data.frame(ID1 = character(),
ID2 = character(),
chemin = character(),
info = character(),
stringsAsFactors = FALSE)
# Recherche des lignes correspondantes à chaque couple
for (cond in select_cond) {
ids <- str_split(cond, ",\\s*")[[1]]
id1 <- ids[1]
id2 <- ids[2]
# Match la ligne contenant les deux identifiants dans le nom du fichier
match_lines <- lines_raw[str_detect(lines_raw, fixed(id1)) &
str_detect(lines_raw, fixed(id2))]
for (line in match_lines) {
# Séparer le chemin et l'info
parts <- str_split(line, ",\\s*")[[1]]
chemin <- parts[1]
info <- ifelse(length(parts) > 1, parts[2], NA)
if (!is.na(chemin) && file.exists(chemin)) {
chemins_trouves <- rbind(
chemins_trouves,
data.frame(ID1 = id1, ID2 = id2, chemin = chemin, info = info,
stringsAsFactors = FALSE)
)
} else {
warning(paste("Fichier introuvable ou chemin invalide:", chemin))
}
}
}
# Importer et annoter les tableaux
list_tables <- list()
for (i in 1:nrow(chemins_trouves)) {
path <- chemins_trouves$chemin[i]
id_label <- paste(chemins_trouves$ID1[i], chemins_trouves$ID2[i],
sep = "_VS_")
info_val <- chemins_trouves$info[i]
df <- tryCatch({
read_delim(path, delim = ",", show_col_types = FALSE)
}, error = function(e) {
warning(paste("Erreur lors de l'import:", path))
return(NULL)
})
if (!is.null(df)) {
df$ID <- id_label
df$Info <- info_val
df_2 <- subset(df,padj < 0.05 & abs(log2FoldChange) > 1 & padj != 0)
#use subset to filter dataframes by columns
list_tables[[length(list_tables) + 1]] <- df_2
}
}## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## • `` -> `...1`# Fusionner tous les tableaux
table_fusionnee <- bind_rows(list_tables)
colnames(table_fusionnee)[1] <- "gene_id"
# Aperçu ou sauvegarde
print(head(table_fusionnee))## # A tibble: 6 × 9
## gene_id baseMean log2FoldChange lfcSE stat pvalue padj ID Info
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 lcl|NC_090… 105. -21.7 2.01 -10.8 4.38e-27 1.56e-22 P_t1… Plant
## 2 lcl|NC_090… 60.1 22.4 2.18 10.3 9.43e-25 1.69e-20 P_t1… Plant
## 3 lcl|NC_090… 51.3 23.3 2.44 9.53 1.60e-21 1.91e-17 P_t1… Plant
## 4 lcl|NC_090… 26.6 -18.9 2.10 -8.97 2.96e-19 2.64e-15 P_t1… Plant
## 5 lcl|NC_090… 196. 26.4 2.97 8.91 5.03e-19 3.59e-15 P_t1… Plant
## 6 lcl|NC_090… 23.2 -19.8 2.36 -8.39 5.02e-17 2.56e-13 P_t1… Plant#write_csv(table_fusionnee, "TopGO/Plant/table_fusionnee.csv")
# Vérifier le nombre de gènes significatifs
cat('Nombre de gènes différentiellement exprimés :',
nrow(table_fusionnee), '\\n')## Nombre de gènes différentiellement exprimés : 6316 \n# Renommer les colonnes du fichier interproscan
colnames(interproscan)[1:2] <- c('GeneID', 'GO')
# Supprimer les lignes sans GO
interproscan <- interproscan[!is.na(interproscan$GO) & interproscan$GO != '', ]
# Associer chaque gène à ses termes GO
gene2GO <- split(interproscan$GO, interproscan$GeneID)
gene2GO <- lapply(gene2GO, function(x) unique(unlist(strsplit(x, ';'))))
# Définir l'univers des gènes et la liste binaire des gènes significatifs
geneUniverse <- names(gene2GO)
ont_list=c("BP", "MF", "CC")
#BP = Biological Process, MF = Molecular Function, CC = Cellular Component2.1.2 Formalisations des données, tests et représentations graphiques
for (i in unique(table_fusionnee$ID)){
table_trimmed = subset(table_fusionnee, ID == i)
up_table = subset(table_trimmed, log2FoldChange >= 1)
down_table = subset(table_trimmed, log2FoldChange <= -1)
geneList_up <- factor(as.integer(geneUniverse %in% up_table$gene_id),
levels = c(0, 1))
geneList_down <- factor(as.integer(geneUniverse %in% down_table$gene_id),
levels = c(0, 1))
for (y in ont_list){
condition = i
orga = table_fusionnee$Info[i]
ontology = y
table(geneList_up)
#check you have significant genes inside the geneUniverse
names(geneList_up) <- geneUniverse
table(geneList_down)
#check you have significant genes inside the geneUniverse
names(geneList_down) <- geneUniverse
# Initialiser l’objet topGO
GOdata_up <- new('topGOdata',
description = "Enrichment analysis",
ontology = y,
allGenes = geneList_up,
annot = annFUN.gene2GO,
geneSelectionFun = function(x) x == 1,
gene2GO = gene2GO,
nodeSize = 5)
GOdata_down <- new('topGOdata',
description = "Enrichment analysis",
ontology = y,
allGenes = geneList_down,
annot = annFUN.gene2GO,
geneSelectionFun = function(x) x == 1,
gene2GO = gene2GO,
nodeSize = 5)
# TEST D’ENRICHISSEMENT GO
resultFisher_wheight01 <- runTest(GOdata_up, algorithm = 'weight01',
statistic = 'fisher')
pValueFisher_wheight01 <- score(resultFisher_wheight01)
resultFisher_classic <- runTest(GOdata_up, algorithm = 'classic',
statistic = 'fisher')
pValueFisher_classic <- score(resultFisher_classic)
# Obtenir les résultats
GOtable_up <- GenTable(GOdata_up, p.value = resultFisher_wheight01,
orderBy = 'p.value', topNodes = 20)
# Sauvegarder les résultats
# write.csv(GOtable_up, paste('TopGO/Plant/TopGO_Up/topGO_results_up_', i,
# '_', y, '.csv'),
# row.names = FALSE)
allRes <- GenTable(GOdata_up, classic = resultFisher_classic,
weight = resultFisher_wheight01, orderBy = "weight",
ranksOf = "weight", topNodes = 20)
knitr::kable(allRes)
# GO.res <-
showSigOfNodes(GOdata_up, score(resultFisher_classic),
firstSigNodes = 20, useInfo = 'all')
resultFisher_wheight01 <- runTest(GOdata_down, algorithm = 'weight01',
statistic = 'fisher')
pValueFisher_wheight01 <- score(resultFisher_wheight01)
resultFisher_classic <- runTest(GOdata_down, algorithm = 'classic',
statistic = 'fisher')
pValueFisher_classic <- score(resultFisher_classic)
# Obtenir les résultats
GOtable_down <- GenTable(GOdata_up, p.value = resultFisher_wheight01,
orderBy = 'p.value', topNodes = 20)
# Sauvegarder les résultats
# write.csv(GOtable_down, paste('TopGO/Plant/TopGO_Down/topGO_results_down_',
# i, '_', y, '.csv'), row.names = FALSE)
# VISUALISATION
GOtable_up_filt <- GOtable_up[as.numeric(GOtable_up$p.value) < 0.05, ]
GOtable_down_filt <- GOtable_down[as.numeric(GOtable_down$p.value) < 0.05, ]
# S'assurer que p.value est bien numérique
GOtable_up_filt$p.value <- as.numeric(GOtable_up_filt$p.value)
GOtable_down_filt$p.value <- as.numeric(GOtable_down_filt$p.value)
# Ajouter une étiquette pour distinguer Up et Down
GOtable_up_filt$Direction <- "Up"
GOtable_down_filt$Direction <- "Down"
# Ajouter la colonne inv_pvalue
GOtable_up_filt$inv_pvalue <- GOtable_up_filt$p.value
# pour les up → identique
GOtable_down_filt$inv_pvalue <- 1 / GOtable_down_filt$p.value
# pour les down → inversée
# Fusionner les deux
GOtable_filt <- rbind(GOtable_up_filt, GOtable_down_filt)
# Tracé avec ggplot
g <- ggplot(GOtable_filt, aes(x = reorder(Term,
-log10(as.numeric(inv_pvalue))),
y = -log10(as.numeric(inv_pvalue)))) +
geom_bar(stat = 'identity', fill = '#00a3a6') +
geom_hline(yintercept = -log10(0.05), color = 'red', linetype = 'dashed',
linewidth = 1) +
geom_hline(yintercept = -log10(1/0.05), color = 'red',
linetype = 'dashed',
linewidth = 1) +
geom_hline(yintercept = 0, color = 'white', linewidth = 0.5) +
coord_flip() +
labs(x = 'Termes GO', y = '-log10[p-value]',
title = i)
print(g)
# ggsave(paste("TopGO/Plant/topGO_results_", i, '_', y, '.pdf'), plot = g)
allRes <- GenTable(GOdata_down, classic = resultFisher_classic,
weight = resultFisher_wheight01, orderBy = "weight",
ranksOf = "weight", topNodes = 20)
knitr::kable(allRes)
# GO.res <-
showSigOfNodes(GOdata_down, topGO::score(resultFisher_classic),
firstSigNodes = 20, useInfo = 'all')
}
}##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 473 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 4 nodes to be scored (0 eliminated genes)##
## Level 11: 9 nodes to be scored (6 eliminated genes)##
## Level 10: 21 nodes to be scored (387 eliminated genes)##
## Level 9: 34 nodes to be scored (551 eliminated genes)##
## Level 8: 56 nodes to be scored (1177 eliminated genes)##
## Level 7: 68 nodes to be scored (4284 eliminated genes)##
## Level 6: 78 nodes to be scored (7383 eliminated genes)##
## Level 5: 84 nodes to be scored (11270 eliminated genes)##
## Level 4: 67 nodes to be scored (15889 eliminated genes)##
## Level 3: 39 nodes to be scored (21158 eliminated genes)##
## Level 2: 11 nodes to be scored (23538 eliminated genes)##
## Level 1: 1 nodes to be scored (24073 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 473 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 305 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 3 nodes to be scored (0 eliminated genes)##
## Level 11: 5 nodes to be scored (0 eliminated genes)##
## Level 10: 11 nodes to be scored (179 eliminated genes)##
## Level 9: 20 nodes to be scored (321 eliminated genes)##
## Level 8: 31 nodes to be scored (820 eliminated genes)##
## Level 7: 39 nodes to be scored (3985 eliminated genes)##
## Level 6: 48 nodes to be scored (6348 eliminated genes)##
## Level 5: 60 nodes to be scored (12015 eliminated genes)##
## Level 4: 51 nodes to be scored (14660 eliminated genes)##
## Level 3: 28 nodes to be scored (20475 eliminated genes)##
## Level 2: 8 nodes to be scored (23154 eliminated genes)##
## Level 1: 1 nodes to be scored (23759 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 305 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 308 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 11 nodes to be scored (60 eliminated genes)##
## Level 8: 26 nodes to be scored (138 eliminated genes)##
## Level 7: 40 nodes to be scored (5958 eliminated genes)##
## Level 6: 57 nodes to be scored (9777 eliminated genes)##
## Level 5: 69 nodes to be scored (11542 eliminated genes)##
## Level 4: 64 nodes to be scored (15445 eliminated genes)##
## Level 3: 23 nodes to be scored (23808 eliminated genes)##
## Level 2: 12 nodes to be scored (26994 eliminated genes)##
## Level 1: 1 nodes to be scored (34273 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 308 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 229 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 5 nodes to be scored (0 eliminated genes)##
## Level 8: 15 nodes to be scored (0 eliminated genes)##
## Level 7: 24 nodes to be scored (5093 eliminated genes)##
## Level 6: 44 nodes to be scored (8563 eliminated genes)##
## Level 5: 54 nodes to be scored (10699 eliminated genes)##
## Level 4: 51 nodes to be scored (14105 eliminated genes)##
## Level 3: 24 nodes to be scored (22459 eliminated genes)##
## Level 2: 11 nodes to be scored (25933 eliminated genes)##
## Level 1: 1 nodes to be scored (34940 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 229 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 68 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 7 nodes to be scored (14 eliminated genes)##
## Level 7: 12 nodes to be scored (14 eliminated genes)##
## Level 6: 10 nodes to be scored (253 eliminated genes)##
## Level 5: 11 nodes to be scored (1162 eliminated genes)##
## Level 4: 13 nodes to be scored (2378 eliminated genes)##
## Level 3: 10 nodes to be scored (4079 eliminated genes)##
## Level 2: 2 nodes to be scored (5195 eliminated genes)##
## Level 1: 1 nodes to be scored (9658 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 68 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 31 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 4 nodes to be scored (0 eliminated genes)##
## Level 7: 4 nodes to be scored (27 eliminated genes)##
## Level 6: 5 nodes to be scored (421 eliminated genes)##
## Level 5: 2 nodes to be scored (1139 eliminated genes)##
## Level 4: 6 nodes to be scored (2998 eliminated genes)##
## Level 3: 6 nodes to be scored (3907 eliminated genes)##
## Level 2: 2 nodes to be scored (4822 eliminated genes)##
## Level 1: 1 nodes to be scored (9000 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 31 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 219 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 3 nodes to be scored (21 eliminated genes)##
## Level 11: 7 nodes to be scored (21 eliminated genes)##
## Level 10: 8 nodes to be scored (62 eliminated genes)##
## Level 9: 14 nodes to be scored (234 eliminated genes)##
## Level 8: 18 nodes to be scored (468 eliminated genes)##
## Level 7: 27 nodes to be scored (3943 eliminated genes)##
## Level 6: 32 nodes to be scored (5084 eliminated genes)##
## Level 5: 42 nodes to be scored (10059 eliminated genes)##
## Level 4: 34 nodes to be scored (12369 eliminated genes)##
## Level 3: 22 nodes to be scored (19645 eliminated genes)##
## Level 2: 9 nodes to be scored (22553 eliminated genes)##
## Level 1: 1 nodes to be scored (23624 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 219 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 249 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 2 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 11 nodes to be scored (132 eliminated genes)##
## Level 9: 18 nodes to be scored (133 eliminated genes)##
## Level 8: 29 nodes to be scored (391 eliminated genes)##
## Level 7: 31 nodes to be scored (3013 eliminated genes)##
## Level 6: 36 nodes to be scored (4379 eliminated genes)##
## Level 5: 45 nodes to be scored (9211 eliminated genes)##
## Level 4: 39 nodes to be scored (12667 eliminated genes)##
## Level 3: 27 nodes to be scored (19251 eliminated genes)##
## Level 2: 8 nodes to be scored (22506 eliminated genes)##
## Level 1: 1 nodes to be scored (23978 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 249 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 174 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 4 nodes to be scored (0 eliminated genes)##
## Level 8: 13 nodes to be scored (0 eliminated genes)##
## Level 7: 21 nodes to be scored (5543 eliminated genes)##
## Level 6: 30 nodes to be scored (8668 eliminated genes)##
## Level 5: 39 nodes to be scored (9509 eliminated genes)##
## Level 4: 41 nodes to be scored (13028 eliminated genes)##
## Level 3: 17 nodes to be scored (21184 eliminated genes)##
## Level 2: 8 nodes to be scored (24809 eliminated genes)##
## Level 1: 1 nodes to be scored (33617 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 174 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 126 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 4 nodes to be scored (60 eliminated genes)##
## Level 8: 6 nodes to be scored (68 eliminated genes)##
## Level 7: 10 nodes to be scored (5031 eliminated genes)##
## Level 6: 19 nodes to be scored (7404 eliminated genes)##
## Level 5: 29 nodes to be scored (9599 eliminated genes)##
## Level 4: 29 nodes to be scored (11950 eliminated genes)##
## Level 3: 17 nodes to be scored (20176 eliminated genes)##
## Level 2: 9 nodes to be scored (23340 eliminated genes)##
## Level 1: 1 nodes to be scored (33343 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 126 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 2 nodes to be scored (0 eliminated genes)##
## Level 5: 4 nodes to be scored (10 eliminated genes)##
## Level 4: 8 nodes to be scored (1583 eliminated genes)##
## Level 3: 6 nodes to be scored (3961 eliminated genes)##
## Level 2: 2 nodes to be scored (4739 eliminated genes)##
## Level 1: 1 nodes to be scored (9517 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher## Warning in arrows(head_from[1], head_from[2], head_to[1], head_to[2], col =
## edgeColor, : zero-length arrow is of indeterminate angle and so skipped
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 39 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 4 nodes to be scored (40 eliminated genes)##
## Level 7: 4 nodes to be scored (47 eliminated genes)##
## Level 6: 6 nodes to be scored (235 eliminated genes)##
## Level 5: 5 nodes to be scored (585 eliminated genes)##
## Level 4: 8 nodes to be scored (2432 eliminated genes)##
## Level 3: 7 nodes to be scored (3927 eliminated genes)##
## Level 2: 2 nodes to be scored (4864 eliminated genes)##
## Level 1: 1 nodes to be scored (9391 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 39 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 161 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 5 nodes to be scored (0 eliminated genes)##
## Level 9: 8 nodes to be scored (133 eliminated genes)##
## Level 8: 20 nodes to be scored (519 eliminated genes)##
## Level 7: 20 nodes to be scored (3015 eliminated genes)##
## Level 6: 25 nodes to be scored (5216 eliminated genes)##
## Level 5: 30 nodes to be scored (8870 eliminated genes)##
## Level 4: 27 nodes to be scored (12597 eliminated genes)##
## Level 3: 18 nodes to be scored (17226 eliminated genes)##
## Level 2: 5 nodes to be scored (21550 eliminated genes)##
## Level 1: 1 nodes to be scored (23508 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 161 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 144 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (59 eliminated genes)##
## Level 9: 6 nodes to be scored (164 eliminated genes)##
## Level 8: 9 nodes to be scored (259 eliminated genes)##
## Level 7: 21 nodes to be scored (2870 eliminated genes)##
## Level 6: 22 nodes to be scored (3716 eliminated genes)##
## Level 5: 30 nodes to be scored (9367 eliminated genes)##
## Level 4: 25 nodes to be scored (11278 eliminated genes)##
## Level 3: 18 nodes to be scored (17993 eliminated genes)##
## Level 2: 6 nodes to be scored (22046 eliminated genes)##
## Level 1: 1 nodes to be scored (23515 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 144 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 132 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 3 nodes to be scored (60 eliminated genes)##
## Level 8: 6 nodes to be scored (68 eliminated genes)##
## Level 7: 10 nodes to be scored (4830 eliminated genes)##
## Level 6: 21 nodes to be scored (7375 eliminated genes)##
## Level 5: 29 nodes to be scored (9216 eliminated genes)##
## Level 4: 33 nodes to be scored (12302 eliminated genes)##
## Level 3: 19 nodes to be scored (20238 eliminated genes)##
## Level 2: 8 nodes to be scored (24561 eliminated genes)##
## Level 1: 1 nodes to be scored (33848 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 132 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 98 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 4 nodes to be scored (0 eliminated genes)##
## Level 7: 6 nodes to be scored (4892 eliminated genes)##
## Level 6: 14 nodes to be scored (5860 eliminated genes)##
## Level 5: 22 nodes to be scored (9482 eliminated genes)##
## Level 4: 23 nodes to be scored (11790 eliminated genes)##
## Level 3: 19 nodes to be scored (18799 eliminated genes)##
## Level 2: 7 nodes to be scored (21393 eliminated genes)##
## Level 1: 1 nodes to be scored (34720 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 98 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 2 nodes to be scored (0 eliminated genes)##
## Level 5: 4 nodes to be scored (10 eliminated genes)##
## Level 4: 9 nodes to be scored (1583 eliminated genes)##
## Level 3: 5 nodes to be scored (3996 eliminated genes)##
## Level 2: 2 nodes to be scored (4883 eliminated genes)##
## Level 1: 1 nodes to be scored (9164 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 27 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 1 nodes to be scored (9 eliminated genes)##
## Level 8: 1 nodes to be scored (25 eliminated genes)##
## Level 7: 3 nodes to be scored (74 eliminated genes)##
## Level 6: 5 nodes to be scored (114 eliminated genes)##
## Level 5: 4 nodes to be scored (164 eliminated genes)##
## Level 4: 5 nodes to be scored (2841 eliminated genes)##
## Level 3: 3 nodes to be scored (3907 eliminated genes)##
## Level 2: 2 nodes to be scored (4776 eliminated genes)##
## Level 1: 1 nodes to be scored (8944 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 27 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 112 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (33 eliminated genes)##
## Level 10: 3 nodes to be scored (231 eliminated genes)##
## Level 9: 6 nodes to be scored (305 eliminated genes)##
## Level 8: 8 nodes to be scored (337 eliminated genes)##
## Level 7: 13 nodes to be scored (3472 eliminated genes)##
## Level 6: 16 nodes to be scored (4922 eliminated genes)##
## Level 5: 21 nodes to be scored (8380 eliminated genes)##
## Level 4: 19 nodes to be scored (11190 eliminated genes)##
## Level 3: 15 nodes to be scored (16526 eliminated genes)##
## Level 2: 6 nodes to be scored (21282 eliminated genes)##
## Level 1: 1 nodes to be scored (23140 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 112 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 139 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (59 eliminated genes)##
## Level 9: 8 nodes to be scored (104 eliminated genes)##
## Level 8: 13 nodes to be scored (277 eliminated genes)##
## Level 7: 21 nodes to be scored (3015 eliminated genes)##
## Level 6: 23 nodes to be scored (3496 eliminated genes)##
## Level 5: 29 nodes to be scored (8186 eliminated genes)##
## Level 4: 18 nodes to be scored (11786 eliminated genes)##
## Level 3: 15 nodes to be scored (17951 eliminated genes)##
## Level 2: 5 nodes to be scored (20593 eliminated genes)##
## Level 1: 1 nodes to be scored (22522 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 139 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 77 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 6 nodes to be scored (4608 eliminated genes)##
## Level 6: 13 nodes to be scored (6968 eliminated genes)##
## Level 5: 16 nodes to be scored (8824 eliminated genes)##
## Level 4: 15 nodes to be scored (11258 eliminated genes)##
## Level 3: 15 nodes to be scored (15371 eliminated genes)##
## Level 2: 7 nodes to be scored (19550 eliminated genes)##
## Level 1: 1 nodes to be scored (31160 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 77 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 119 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 13 nodes to be scored (4608 eliminated genes)##
## Level 6: 21 nodes to be scored (7912 eliminated genes)##
## Level 5: 26 nodes to be scored (9435 eliminated genes)##
## Level 4: 29 nodes to be scored (11687 eliminated genes)##
## Level 3: 15 nodes to be scored (19910 eliminated genes)##
## Level 2: 7 nodes to be scored (24055 eliminated genes)##
## Level 1: 1 nodes to be scored (33465 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 119 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 22 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 2 nodes to be scored (0 eliminated genes)##
## Level 6: 3 nodes to be scored (68 eliminated genes)##
## Level 5: 3 nodes to be scored (134 eliminated genes)##
## Level 4: 5 nodes to be scored (2654 eliminated genes)##
## Level 3: 5 nodes to be scored (3921 eliminated genes)##
## Level 2: 2 nodes to be scored (4632 eliminated genes)##
## Level 1: 1 nodes to be scored (9344 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 22 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 18 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 6: 2 nodes to be scored (0 eliminated genes)##
## Level 5: 3 nodes to be scored (0 eliminated genes)##
## Level 4: 4 nodes to be scored (1610 eliminated genes)##
## Level 3: 6 nodes to be scored (2412 eliminated genes)##
## Level 2: 2 nodes to be scored (4631 eliminated genes)##
## Level 1: 1 nodes to be scored (9343 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 18 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 387 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 2 nodes to be scored (0 eliminated genes)##
## Level 11: 5 nodes to be scored (0 eliminated genes)##
## Level 10: 13 nodes to be scored (84 eliminated genes)##
## Level 9: 23 nodes to be scored (270 eliminated genes)##
## Level 8: 45 nodes to be scored (853 eliminated genes)##
## Level 7: 60 nodes to be scored (3892 eliminated genes)##
## Level 6: 57 nodes to be scored (6812 eliminated genes)##
## Level 5: 72 nodes to be scored (12823 eliminated genes)##
## Level 4: 63 nodes to be scored (15041 eliminated genes)##
## Level 3: 36 nodes to be scored (20769 eliminated genes)##
## Level 2: 10 nodes to be scored (23158 eliminated genes)##
## Level 1: 1 nodes to be scored (23671 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 387 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 353 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 3 nodes to be scored (0 eliminated genes)##
## Level 11: 3 nodes to be scored (0 eliminated genes)##
## Level 10: 9 nodes to be scored (344 eliminated genes)##
## Level 9: 23 nodes to be scored (367 eliminated genes)##
## Level 8: 35 nodes to be scored (710 eliminated genes)##
## Level 7: 55 nodes to be scored (4156 eliminated genes)##
## Level 6: 59 nodes to be scored (6984 eliminated genes)##
## Level 5: 69 nodes to be scored (12787 eliminated genes)##
## Level 4: 48 nodes to be scored (15428 eliminated genes)##
## Level 3: 37 nodes to be scored (20470 eliminated genes)##
## Level 2: 11 nodes to be scored (22900 eliminated genes)##
## Level 1: 1 nodes to be scored (24130 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 353 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 292 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (0 eliminated genes)##
## Level 8: 21 nodes to be scored (75 eliminated genes)##
## Level 7: 36 nodes to be scored (5532 eliminated genes)##
## Level 6: 58 nodes to be scored (9471 eliminated genes)##
## Level 5: 69 nodes to be scored (11629 eliminated genes)##
## Level 4: 60 nodes to be scored (15203 eliminated genes)##
## Level 3: 25 nodes to be scored (23767 eliminated genes)##
## Level 2: 13 nodes to be scored (26626 eliminated genes)##
## Level 1: 1 nodes to be scored (35035 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 292 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 247 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 8 nodes to be scored (0 eliminated genes)##
## Level 8: 25 nodes to be scored (47 eliminated genes)##
## Level 7: 34 nodes to be scored (5664 eliminated genes)##
## Level 6: 51 nodes to be scored (9313 eliminated genes)##
## Level 5: 48 nodes to be scored (10695 eliminated genes)##
## Level 4: 47 nodes to be scored (15159 eliminated genes)##
## Level 3: 22 nodes to be scored (23442 eliminated genes)##
## Level 2: 9 nodes to be scored (26344 eliminated genes)##
## Level 1: 1 nodes to be scored (34178 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 247 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 90 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 4 nodes to be scored (0 eliminated genes)##
## Level 10: 5 nodes to be scored (13 eliminated genes)##
## Level 9: 7 nodes to be scored (31 eliminated genes)##
## Level 8: 8 nodes to be scored (78 eliminated genes)##
## Level 7: 11 nodes to be scored (109 eliminated genes)##
## Level 6: 13 nodes to be scored (558 eliminated genes)##
## Level 5: 15 nodes to be scored (1290 eliminated genes)##
## Level 4: 15 nodes to be scored (2976 eliminated genes)##
## Level 3: 8 nodes to be scored (4192 eliminated genes)##
## Level 2: 2 nodes to be scored (5244 eliminated genes)##
## Level 1: 1 nodes to be scored (9611 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 90 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 42 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 3 nodes to be scored (90 eliminated genes)##
## Level 6: 7 nodes to be scored (237 eliminated genes)##
## Level 5: 7 nodes to be scored (824 eliminated genes)##
## Level 4: 8 nodes to be scored (2118 eliminated genes)##
## Level 3: 9 nodes to be scored (4166 eliminated genes)##
## Level 2: 2 nodes to be scored (4848 eliminated genes)##
## Level 1: 1 nodes to be scored (9495 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 42 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 203 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 2 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (33 eliminated genes)##
## Level 10: 6 nodes to be scored (339 eliminated genes)##
## Level 9: 15 nodes to be scored (346 eliminated genes)##
## Level 8: 21 nodes to be scored (787 eliminated genes)##
## Level 7: 26 nodes to be scored (3776 eliminated genes)##
## Level 6: 32 nodes to be scored (5699 eliminated genes)##
## Level 5: 35 nodes to be scored (10771 eliminated genes)##
## Level 4: 32 nodes to be scored (13695 eliminated genes)##
## Level 3: 24 nodes to be scored (19443 eliminated genes)##
## Level 2: 6 nodes to be scored (22037 eliminated genes)##
## Level 1: 1 nodes to be scored (23570 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 203 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 160 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (33 eliminated genes)##
## Level 9: 11 nodes to be scored (53 eliminated genes)##
## Level 8: 14 nodes to be scored (56 eliminated genes)##
## Level 7: 21 nodes to be scored (3699 eliminated genes)##
## Level 6: 23 nodes to be scored (4891 eliminated genes)##
## Level 5: 30 nodes to be scored (9339 eliminated genes)##
## Level 4: 26 nodes to be scored (12394 eliminated genes)##
## Level 3: 21 nodes to be scored (19201 eliminated genes)##
## Level 2: 8 nodes to be scored (22464 eliminated genes)##
## Level 1: 1 nodes to be scored (23807 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 160 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 110 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 13 nodes to be scored (4608 eliminated genes)##
## Level 6: 17 nodes to be scored (7881 eliminated genes)##
## Level 5: 22 nodes to be scored (10114 eliminated genes)##
## Level 4: 26 nodes to be scored (12227 eliminated genes)##
## Level 3: 17 nodes to be scored (19578 eliminated genes)##
## Level 2: 7 nodes to be scored (24111 eliminated genes)##
## Level 1: 1 nodes to be scored (34217 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 110 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 137 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 12 nodes to be scored (0 eliminated genes)##
## Level 7: 19 nodes to be scored (4926 eliminated genes)##
## Level 6: 27 nodes to be scored (7988 eliminated genes)##
## Level 5: 27 nodes to be scored (9660 eliminated genes)##
## Level 4: 24 nodes to be scored (12422 eliminated genes)##
## Level 3: 17 nodes to be scored (20397 eliminated genes)##
## Level 2: 7 nodes to be scored (23436 eliminated genes)##
## Level 1: 1 nodes to be scored (33252 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 137 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 1 nodes to be scored (17 eliminated genes)##
## Level 8: 1 nodes to be scored (20 eliminated genes)##
## Level 7: 3 nodes to be scored (22 eliminated genes)##
## Level 6: 5 nodes to be scored (79 eliminated genes)##
## Level 5: 5 nodes to be scored (301 eliminated genes)##
## Level 4: 7 nodes to be scored (2694 eliminated genes)##
## Level 3: 8 nodes to be scored (3969 eliminated genes)##
## Level 2: 2 nodes to be scored (4189 eliminated genes)##
## Level 1: 1 nodes to be scored (9611 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 25 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 6: 2 nodes to be scored (0 eliminated genes)##
## Level 5: 4 nodes to be scored (0 eliminated genes)##
## Level 4: 9 nodes to be scored (1565 eliminated genes)##
## Level 3: 7 nodes to be scored (2431 eliminated genes)##
## Level 2: 2 nodes to be scored (5092 eliminated genes)##
## Level 1: 1 nodes to be scored (9611 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 25 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 499 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 4 nodes to be scored (0 eliminated genes)##
## Level 11: 10 nodes to be scored (0 eliminated genes)##
## Level 10: 22 nodes to be scored (215 eliminated genes)##
## Level 9: 34 nodes to be scored (465 eliminated genes)##
## Level 8: 51 nodes to be scored (1064 eliminated genes)##
## Level 7: 72 nodes to be scored (3910 eliminated genes)##
## Level 6: 84 nodes to be scored (5752 eliminated genes)##
## Level 5: 96 nodes to be scored (12003 eliminated genes)##
## Level 4: 72 nodes to be scored (15153 eliminated genes)##
## Level 3: 41 nodes to be scored (21043 eliminated genes)##
## Level 2: 12 nodes to be scored (23235 eliminated genes)##
## Level 1: 1 nodes to be scored (24036 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 499 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 299 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 3 nodes to be scored (0 eliminated genes)##
## Level 11: 8 nodes to be scored (6 eliminated genes)##
## Level 10: 14 nodes to be scored (90 eliminated genes)##
## Level 9: 26 nodes to be scored (137 eliminated genes)##
## Level 8: 31 nodes to be scored (784 eliminated genes)##
## Level 7: 41 nodes to be scored (4247 eliminated genes)##
## Level 6: 47 nodes to be scored (6399 eliminated genes)##
## Level 5: 46 nodes to be scored (12385 eliminated genes)##
## Level 4: 41 nodes to be scored (15159 eliminated genes)##
## Level 3: 31 nodes to be scored (20156 eliminated genes)##
## Level 2: 9 nodes to be scored (22865 eliminated genes)##
## Level 1: 1 nodes to be scored (23761 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 299 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 313 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 8 nodes to be scored (0 eliminated genes)##
## Level 8: 25 nodes to be scored (10 eliminated genes)##
## Level 7: 40 nodes to be scored (5767 eliminated genes)##
## Level 6: 56 nodes to be scored (9880 eliminated genes)##
## Level 5: 67 nodes to be scored (11624 eliminated genes)##
## Level 4: 69 nodes to be scored (14890 eliminated genes)##
## Level 3: 33 nodes to be scored (23581 eliminated genes)##
## Level 2: 13 nodes to be scored (26925 eliminated genes)##
## Level 1: 1 nodes to be scored (35151 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 313 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 208 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 5 nodes to be scored (0 eliminated genes)##
## Level 8: 16 nodes to be scored (0 eliminated genes)##
## Level 7: 24 nodes to be scored (5575 eliminated genes)##
## Level 6: 39 nodes to be scored (9021 eliminated genes)##
## Level 5: 48 nodes to be scored (10474 eliminated genes)##
## Level 4: 45 nodes to be scored (13428 eliminated genes)##
## Level 3: 22 nodes to be scored (22311 eliminated genes)##
## Level 2: 8 nodes to be scored (25908 eliminated genes)##
## Level 1: 1 nodes to be scored (34832 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 208 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 65 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 4 nodes to be scored (15 eliminated genes)##
## Level 8: 4 nodes to be scored (31 eliminated genes)##
## Level 7: 9 nodes to be scored (176 eliminated genes)##
## Level 6: 10 nodes to be scored (449 eliminated genes)##
## Level 5: 9 nodes to be scored (1179 eliminated genes)##
## Level 4: 12 nodes to be scored (3702 eliminated genes)##
## Level 3: 10 nodes to be scored (4040 eliminated genes)##
## Level 2: 2 nodes to be scored (5165 eliminated genes)##
## Level 1: 1 nodes to be scored (9668 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 65 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 47 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 5 nodes to be scored (26 eliminated genes)##
## Level 7: 8 nodes to be scored (38 eliminated genes)##
## Level 6: 6 nodes to be scored (322 eliminated genes)##
## Level 5: 7 nodes to be scored (1118 eliminated genes)##
## Level 4: 8 nodes to be scored (3027 eliminated genes)##
## Level 3: 6 nodes to be scored (3936 eliminated genes)##
## Level 2: 2 nodes to be scored (4877 eliminated genes)##
## Level 1: 1 nodes to be scored (9217 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 47 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 636 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 15: 1 nodes to be scored (0 eliminated genes)##
## Level 14: 2 nodes to be scored (0 eliminated genes)##
## Level 13: 4 nodes to be scored (16 eliminated genes)##
## Level 12: 11 nodes to be scored (29 eliminated genes)##
## Level 11: 18 nodes to be scored (35 eliminated genes)##
## Level 10: 33 nodes to be scored (492 eliminated genes)##
## Level 9: 50 nodes to be scored (697 eliminated genes)##
## Level 8: 74 nodes to be scored (1558 eliminated genes)##
## Level 7: 110 nodes to be scored (5138 eliminated genes)##
## Level 6: 108 nodes to be scored (7604 eliminated genes)##
## Level 5: 110 nodes to be scored (14223 eliminated genes)##
## Level 4: 65 nodes to be scored (16427 eliminated genes)##
## Level 3: 40 nodes to be scored (21426 eliminated genes)##
## Level 2: 9 nodes to be scored (23250 eliminated genes)##
## Level 1: 1 nodes to be scored (24151 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 636 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 550 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 2 nodes to be scored (0 eliminated genes)##
## Level 12: 6 nodes to be scored (0 eliminated genes)##
## Level 11: 9 nodes to be scored (19 eliminated genes)##
## Level 10: 31 nodes to be scored (223 eliminated genes)##
## Level 9: 59 nodes to be scored (494 eliminated genes)##
## Level 8: 76 nodes to be scored (1317 eliminated genes)##
## Level 7: 83 nodes to be scored (5156 eliminated genes)##
## Level 6: 82 nodes to be scored (8112 eliminated genes)##
## Level 5: 88 nodes to be scored (14026 eliminated genes)##
## Level 4: 65 nodes to be scored (15871 eliminated genes)##
## Level 3: 39 nodes to be scored (20819 eliminated genes)##
## Level 2: 9 nodes to be scored (23472 eliminated genes)##
## Level 1: 1 nodes to be scored (24090 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 550 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 361 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 8 nodes to be scored (0 eliminated genes)##
## Level 8: 29 nodes to be scored (10 eliminated genes)##
## Level 7: 49 nodes to be scored (5693 eliminated genes)##
## Level 6: 70 nodes to be scored (9945 eliminated genes)##
## Level 5: 80 nodes to be scored (11800 eliminated genes)##
## Level 4: 77 nodes to be scored (15544 eliminated genes)##
## Level 3: 31 nodes to be scored (24412 eliminated genes)##
## Level 2: 15 nodes to be scored (27514 eliminated genes)##
## Level 1: 1 nodes to be scored (34973 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 361 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 359 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 13 nodes to be scored (60 eliminated genes)##
## Level 8: 31 nodes to be scored (143 eliminated genes)##
## Level 7: 47 nodes to be scored (5958 eliminated genes)##
## Level 6: 81 nodes to be scored (9809 eliminated genes)##
## Level 5: 71 nodes to be scored (11839 eliminated genes)##
## Level 4: 69 nodes to be scored (16204 eliminated genes)##
## Level 3: 27 nodes to be scored (23960 eliminated genes)##
## Level 2: 14 nodes to be scored (27294 eliminated genes)##
## Level 1: 1 nodes to be scored (35103 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 359 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 112 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 5 nodes to be scored (0 eliminated genes)##
## Level 10: 7 nodes to be scored (13 eliminated genes)##
## Level 9: 7 nodes to be scored (59 eliminated genes)##
## Level 8: 12 nodes to be scored (106 eliminated genes)##
## Level 7: 14 nodes to be scored (145 eliminated genes)##
## Level 6: 14 nodes to be scored (736 eliminated genes)##
## Level 5: 17 nodes to be scored (1571 eliminated genes)##
## Level 4: 19 nodes to be scored (3577 eliminated genes)##
## Level 3: 13 nodes to be scored (4205 eliminated genes)##
## Level 2: 2 nodes to be scored (5350 eliminated genes)##
## Level 1: 1 nodes to be scored (9658 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 112 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 97 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (0 eliminated genes)##
## Level 8: 12 nodes to be scored (81 eliminated genes)##
## Level 7: 13 nodes to be scored (184 eliminated genes)##
## Level 6: 15 nodes to be scored (737 eliminated genes)##
## Level 5: 15 nodes to be scored (1625 eliminated genes)##
## Level 4: 14 nodes to be scored (3765 eliminated genes)##
## Level 3: 14 nodes to be scored (4221 eliminated genes)##
## Level 2: 2 nodes to be scored (5193 eliminated genes)##
## Level 1: 1 nodes to be scored (9552 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 97 nontrivial nodes
## parameters:
## test statistic: fisher
## Warning in arrows(head_from[1], head_from[2], head_to[1], head_to[2], col =
## edgeColor, : zero-length arrow is of indeterminate angle and so skipped
## Warning in arrows(head_from[1], head_from[2], head_to[1], head_to[2], col =
## edgeColor, : zero-length arrow is of indeterminate angle and so skipped
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 484 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 5 nodes to be scored (0 eliminated genes)##
## Level 11: 7 nodes to be scored (6 eliminated genes)##
## Level 10: 26 nodes to be scored (205 eliminated genes)##
## Level 9: 41 nodes to be scored (219 eliminated genes)##
## Level 8: 64 nodes to be scored (1057 eliminated genes)##
## Level 7: 70 nodes to be scored (4518 eliminated genes)##
## Level 6: 76 nodes to be scored (7288 eliminated genes)##
## Level 5: 83 nodes to be scored (12636 eliminated genes)##
## Level 4: 63 nodes to be scored (15851 eliminated genes)##
## Level 3: 37 nodes to be scored (20892 eliminated genes)##
## Level 2: 10 nodes to be scored (23501 eliminated genes)##
## Level 1: 1 nodes to be scored (24028 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 484 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 452 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 15: 1 nodes to be scored (0 eliminated genes)##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 2 nodes to be scored (16 eliminated genes)##
## Level 12: 10 nodes to be scored (21 eliminated genes)##
## Level 11: 15 nodes to be scored (26 eliminated genes)##
## Level 10: 26 nodes to be scored (261 eliminated genes)##
## Level 9: 38 nodes to be scored (441 eliminated genes)##
## Level 8: 56 nodes to be scored (1192 eliminated genes)##
## Level 7: 64 nodes to be scored (4264 eliminated genes)##
## Level 6: 68 nodes to be scored (6981 eliminated genes)##
## Level 5: 78 nodes to be scored (12343 eliminated genes)##
## Level 4: 53 nodes to be scored (14731 eliminated genes)##
## Level 3: 30 nodes to be scored (20550 eliminated genes)##
## Level 2: 9 nodes to be scored (23152 eliminated genes)##
## Level 1: 1 nodes to be scored (23749 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 452 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 309 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 10 nodes to be scored (60 eliminated genes)##
## Level 8: 24 nodes to be scored (154 eliminated genes)##
## Level 7: 38 nodes to be scored (5908 eliminated genes)##
## Level 6: 57 nodes to be scored (9900 eliminated genes)##
## Level 5: 73 nodes to be scored (11632 eliminated genes)##
## Level 4: 64 nodes to be scored (15188 eliminated genes)##
## Level 3: 25 nodes to be scored (24083 eliminated genes)##
## Level 2: 12 nodes to be scored (27051 eliminated genes)##
## Level 1: 1 nodes to be scored (34423 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 309 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 264 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (0 eliminated genes)##
## Level 8: 15 nodes to be scored (23 eliminated genes)##
## Level 7: 35 nodes to be scored (5148 eliminated genes)##
## Level 6: 52 nodes to be scored (8548 eliminated genes)##
## Level 5: 64 nodes to be scored (11188 eliminated genes)##
## Level 4: 53 nodes to be scored (14728 eliminated genes)##
## Level 3: 25 nodes to be scored (23961 eliminated genes)##
## Level 2: 11 nodes to be scored (26503 eliminated genes)##
## Level 1: 1 nodes to be scored (34850 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 264 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 82 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 10 nodes to be scored (54 eliminated genes)##
## Level 7: 13 nodes to be scored (61 eliminated genes)##
## Level 6: 12 nodes to be scored (491 eliminated genes)##
## Level 5: 14 nodes to be scored (1587 eliminated genes)##
## Level 4: 16 nodes to be scored (2848 eliminated genes)##
## Level 3: 10 nodes to be scored (4099 eliminated genes)##
## Level 2: 2 nodes to be scored (5379 eliminated genes)##
## Level 1: 1 nodes to be scored (9668 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 82 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 3 nodes to be scored (12 eliminated genes)##
## Level 7: 4 nodes to be scored (24 eliminated genes)##
## Level 6: 5 nodes to be scored (410 eliminated genes)##
## Level 5: 4 nodes to be scored (971 eliminated genes)##
## Level 4: 7 nodes to be scored (2913 eliminated genes)##
## Level 3: 7 nodes to be scored (3918 eliminated genes)##
## Level 2: 2 nodes to be scored (4830 eliminated genes)##
## Level 1: 1 nodes to be scored (9217 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 221 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 3 nodes to be scored (21 eliminated genes)##
## Level 11: 6 nodes to be scored (21 eliminated genes)##
## Level 10: 6 nodes to be scored (62 eliminated genes)##
## Level 9: 12 nodes to be scored (225 eliminated genes)##
## Level 8: 14 nodes to be scored (416 eliminated genes)##
## Level 7: 25 nodes to be scored (3750 eliminated genes)##
## Level 6: 35 nodes to be scored (4949 eliminated genes)##
## Level 5: 45 nodes to be scored (10446 eliminated genes)##
## Level 4: 38 nodes to be scored (12892 eliminated genes)##
## Level 3: 26 nodes to be scored (19700 eliminated genes)##
## Level 2: 8 nodes to be scored (22883 eliminated genes)##
## Level 1: 1 nodes to be scored (23935 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 221 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 200 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (0 eliminated genes)##
## Level 9: 8 nodes to be scored (15 eliminated genes)##
## Level 8: 20 nodes to be scored (130 eliminated genes)##
## Level 7: 30 nodes to be scored (3043 eliminated genes)##
## Level 6: 37 nodes to be scored (4709 eliminated genes)##
## Level 5: 39 nodes to be scored (9271 eliminated genes)##
## Level 4: 33 nodes to be scored (13513 eliminated genes)##
## Level 3: 20 nodes to be scored (18253 eliminated genes)##
## Level 2: 8 nodes to be scored (22910 eliminated genes)##
## Level 1: 1 nodes to be scored (23887 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 200 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 186 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 4 nodes to be scored (0 eliminated genes)##
## Level 8: 13 nodes to be scored (0 eliminated genes)##
## Level 7: 19 nodes to be scored (5543 eliminated genes)##
## Level 6: 33 nodes to be scored (8665 eliminated genes)##
## Level 5: 43 nodes to be scored (9341 eliminated genes)##
## Level 4: 43 nodes to be scored (13180 eliminated genes)##
## Level 3: 19 nodes to be scored (21091 eliminated genes)##
## Level 2: 11 nodes to be scored (24823 eliminated genes)##
## Level 1: 1 nodes to be scored (34270 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 186 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 123 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 4 nodes to be scored (60 eliminated genes)##
## Level 8: 9 nodes to be scored (84 eliminated genes)##
## Level 7: 14 nodes to be scored (4995 eliminated genes)##
## Level 6: 18 nodes to be scored (7668 eliminated genes)##
## Level 5: 26 nodes to be scored (10505 eliminated genes)##
## Level 4: 26 nodes to be scored (12195 eliminated genes)##
## Level 3: 14 nodes to be scored (20261 eliminated genes)##
## Level 2: 8 nodes to be scored (24120 eliminated genes)##
## Level 1: 1 nodes to be scored (32363 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 123 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 42 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 2 nodes to be scored (12 eliminated genes)##
## Level 8: 3 nodes to be scored (26 eliminated genes)##
## Level 7: 3 nodes to be scored (38 eliminated genes)##
## Level 6: 3 nodes to be scored (176 eliminated genes)##
## Level 5: 6 nodes to be scored (961 eliminated genes)##
## Level 4: 11 nodes to be scored (2654 eliminated genes)##
## Level 3: 8 nodes to be scored (3972 eliminated genes)##
## Level 2: 2 nodes to be scored (4934 eliminated genes)##
## Level 1: 1 nodes to be scored (9611 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 42 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 6: 1 nodes to be scored (0 eliminated genes)##
## Level 5: 5 nodes to be scored (0 eliminated genes)##
## Level 4: 8 nodes to be scored (1551 eliminated genes)##
## Level 3: 7 nodes to be scored (2452 eliminated genes)##
## Level 2: 2 nodes to be scored (4853 eliminated genes)##
## Level 1: 1 nodes to be scored (9611 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 138 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 5 nodes to be scored (7 eliminated genes)##
## Level 8: 13 nodes to be scored (184 eliminated genes)##
## Level 7: 20 nodes to be scored (2843 eliminated genes)##
## Level 6: 23 nodes to be scored (4523 eliminated genes)##
## Level 5: 30 nodes to be scored (10100 eliminated genes)##
## Level 4: 21 nodes to be scored (12019 eliminated genes)##
## Level 3: 17 nodes to be scored (18436 eliminated genes)##
## Level 2: 5 nodes to be scored (20649 eliminated genes)##
## Level 1: 1 nodes to be scored (22544 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 138 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 116 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 5 nodes to be scored (67 eliminated genes)##
## Level 8: 10 nodes to be scored (75 eliminated genes)##
## Level 7: 16 nodes to be scored (2850 eliminated genes)##
## Level 6: 19 nodes to be scored (3951 eliminated genes)##
## Level 5: 24 nodes to be scored (8674 eliminated genes)##
## Level 4: 19 nodes to be scored (11285 eliminated genes)##
## Level 3: 14 nodes to be scored (16000 eliminated genes)##
## Level 2: 5 nodes to be scored (21414 eliminated genes)##
## Level 1: 1 nodes to be scored (23464 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 116 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 106 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 4 nodes to be scored (0 eliminated genes)##
## Level 7: 10 nodes to be scored (4608 eliminated genes)##
## Level 6: 18 nodes to be scored (7057 eliminated genes)##
## Level 5: 23 nodes to be scored (8900 eliminated genes)##
## Level 4: 26 nodes to be scored (11155 eliminated genes)##
## Level 3: 15 nodes to be scored (17408 eliminated genes)##
## Level 2: 8 nodes to be scored (22884 eliminated genes)##
## Level 1: 1 nodes to be scored (33757 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 106 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 72 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 2 nodes to be scored (0 eliminated genes)##
## Level 7: 5 nodes to be scored (4892 eliminated genes)##
## Level 6: 11 nodes to be scored (6947 eliminated genes)##
## Level 5: 14 nodes to be scored (9202 eliminated genes)##
## Level 4: 13 nodes to be scored (11195 eliminated genes)##
## Level 3: 16 nodes to be scored (17099 eliminated genes)##
## Level 2: 8 nodes to be scored (18549 eliminated genes)##
## Level 1: 1 nodes to be scored (33254 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 72 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 23 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 2 nodes to be scored (0 eliminated genes)##
## Level 6: 4 nodes to be scored (49 eliminated genes)##
## Level 5: 3 nodes to be scored (127 eliminated genes)##
## Level 4: 4 nodes to be scored (2470 eliminated genes)##
## Level 3: 6 nodes to be scored (3966 eliminated genes)##
## Level 2: 2 nodes to be scored (4615 eliminated genes)##
## Level 1: 1 nodes to be scored (9058 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 23 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 30 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 1 nodes to be scored (9 eliminated genes)##
## Level 8: 2 nodes to be scored (25 eliminated genes)##
## Level 7: 4 nodes to be scored (74 eliminated genes)##
## Level 6: 6 nodes to be scored (182 eliminated genes)##
## Level 5: 4 nodes to be scored (299 eliminated genes)##
## Level 4: 5 nodes to be scored (3200 eliminated genes)##
## Level 3: 3 nodes to be scored (3907 eliminated genes)##
## Level 2: 2 nodes to be scored (4776 eliminated genes)##
## Level 1: 1 nodes to be scored (8944 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 30 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1284 GO terms found. )##
## Build GO DAG topology ..........## ( 2894 GO terms and 5659 relations. )##
## Annotating nodes ...............## ( 24345 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 123 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 3 nodes to be scored (33 eliminated genes)##
## Level 10: 4 nodes to be scored (231 eliminated genes)##
## Level 9: 7 nodes to be scored (312 eliminated genes)##
## Level 8: 7 nodes to be scored (438 eliminated genes)##
## Level 7: 14 nodes to be scored (3649 eliminated genes)##
## Level 6: 17 nodes to be scored (4870 eliminated genes)##
## Level 5: 24 nodes to be scored (8824 eliminated genes)##
## Level 4: 22 nodes to be scored (10075 eliminated genes)##
## Level 3: 16 nodes to be scored (16653 eliminated genes)##
## Level 2: 6 nodes to be scored (21364 eliminated genes)##
## Level 1: 1 nodes to be scored (23529 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 123 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 183 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (11 eliminated genes)##
## Level 8: 21 nodes to be scored (132 eliminated genes)##
## Level 7: 21 nodes to be scored (2948 eliminated genes)##
## Level 6: 25 nodes to be scored (5335 eliminated genes)##
## Level 5: 37 nodes to be scored (9125 eliminated genes)##
## Level 4: 36 nodes to be scored (13048 eliminated genes)##
## Level 3: 22 nodes to be scored (15840 eliminated genes)##
## Level 2: 8 nodes to be scored (21895 eliminated genes)##
## Level 1: 1 nodes to be scored (23545 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 183 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1346 GO terms found. )##
## Build GO DAG topology ..........## ( 1777 GO terms and 2313 relations. )##
## Annotating nodes ...............## ( 35716 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 83 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 7 nodes to be scored (4608 eliminated genes)##
## Level 6: 14 nodes to be scored (6968 eliminated genes)##
## Level 5: 20 nodes to be scored (8843 eliminated genes)##
## Level 4: 16 nodes to be scored (11494 eliminated genes)##
## Level 3: 15 nodes to be scored (18373 eliminated genes)##
## Level 2: 6 nodes to be scored (20441 eliminated genes)##
## Level 1: 1 nodes to be scored (31993 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 83 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 133 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 2 nodes to be scored (60 eliminated genes)##
## Level 8: 6 nodes to be scored (68 eliminated genes)##
## Level 7: 10 nodes to be scored (4695 eliminated genes)##
## Level 6: 20 nodes to be scored (7855 eliminated genes)##
## Level 5: 30 nodes to be scored (9090 eliminated genes)##
## Level 4: 33 nodes to be scored (11839 eliminated genes)##
## Level 3: 19 nodes to be scored (20314 eliminated genes)##
## Level 2: 10 nodes to be scored (23550 eliminated genes)##
## Level 1: 1 nodes to be scored (33848 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 133 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 379 GO terms found. )##
## Build GO DAG topology ..........## ( 608 GO terms and 1042 relations. )##
## Annotating nodes ...............## ( 9775 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 19 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 3 nodes to be scored (0 eliminated genes)##
## Level 5: 3 nodes to be scored (17 eliminated genes)##
## Level 4: 5 nodes to be scored (2654 eliminated genes)##
## Level 3: 4 nodes to be scored (3921 eliminated genes)##
## Level 2: 2 nodes to be scored (4632 eliminated genes)##
## Level 1: 1 nodes to be scored (9297 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 19 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 28 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 2 nodes to be scored (68 eliminated genes)##
## Level 5: 5 nodes to be scored (135 eliminated genes)##
## Level 4: 10 nodes to be scored (1911 eliminated genes)##
## Level 3: 6 nodes to be scored (4010 eliminated genes)##
## Level 2: 2 nodes to be scored (4900 eliminated genes)##
## Level 1: 1 nodes to be scored (9517 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 28 nontrivial nodes
## parameters:
## test statistic: fisher
2.2 Insect
2.2.1 Import des données pour l’analyse TopGO sur les échantillons issus des insect
# Annotations GO (InterProScan)
interproscan <- read.delim('TopGO/Insect/gene_GO.txt',
header = FALSE, sep = '\t')
head(interproscan)## V1 V2
## 1 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294_orf25253 GO:0003883
## 2 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294_orf25253 GO:0006241
## 3 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294_orf25253 GO:0003883
## 4 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294_orf25253 GO:0006221
## 5 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294_orf25253 GO:0003883
## 6 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294_orf25253 GO:0006221interproscan$V1 <- vapply(interproscan$V1,
function(x) gsub('_orf[0-9]+', '', x), character(1))
#take out the orf part
interproscan <- as.data.frame(interproscan)
head(interproscan)## V1 V2
## 1 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294 GO:0003883
## 2 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294 GO:0006241
## 3 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294 GO:0003883
## 4 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294 GO:0006221
## 5 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294 GO:0003883
## 6 lcl|NZ_CACTIE010000113.1_cds_WP_181994785.1_1294 GO:0006221# Vérifier la structure des fichiers
if (ncol(interproscan) < 2)
stop('Erreur : Le fichier interproscan semble mal formaté.')
# Définir la liste des conditions d’intérêt
select_cond=c("B_t1_Q11L, B_t1_Q11V_L", "B_t1_Q21L, B_t1_Q21V_L", "B_t2_Q11L,
B_t2_Q11V_L", "B_t2_Q21L, B_t2_Q21V_L", "B_t1_Q11V_L,
B_t2_Q11V_L", "B_t1_Q21V_L, B_t2_Q21V_L", "B_t1_Q11L, B_t2_Q11L",
"B_t1_Q21L, B_t2_Q21L", "B_t1_Q11L, B_t1_Q21L", "B_t1_Q11V_L,
B_t1_Q21V_L", "B_t2_Q11L, B_t2_Q21L", "B_t2_Q11V_L, B_t2_Q21V_L")
# Lire les lignes du fichier contenant les chemins et infos
lines_raw <- readLines("TopGO/Insect/liste_deseq.txt")
# Initialiser une liste de résultats
chemins_trouves <- data.frame(ID1 = character(),
ID2 = character(),
chemin = character(),
info = character(),
stringsAsFactors = FALSE)
# Recherche des lignes correspondantes à chaque couple
for (cond in select_cond) {
ids <- str_split(cond, ",\\s*")[[1]]
id1 <- ids[1]
id2 <- ids[2]
# Match la ligne contenant les deux identifiants dans le nom du fichier
match_lines <- lines_raw[str_detect(lines_raw, fixed(id1)) &
str_detect(lines_raw, fixed(id2))]
for (line in match_lines) {
# Séparer le chemin et l'info
parts <- str_split(line, ",\\s*")[[1]]
chemin <- parts[1]
info <- ifelse(length(parts) > 1, parts[2], NA)
if (!is.na(chemin) && file.exists(chemin)) {
chemins_trouves <- rbind(
chemins_trouves,
data.frame(ID1 = id1, ID2 = id2, chemin = chemin, info = info,
stringsAsFactors = FALSE)
)
} else {
warning(paste("Fichier introuvable ou chemin invalide:", chemin))
}
}
}
# Importer et annoter les tableaux
list_tables <- list()
for (i in 1:nrow(chemins_trouves)) {
path <- chemins_trouves$chemin[i]
id_label <- paste(chemins_trouves$ID1[i], chemins_trouves$ID2[i],
sep = "_VS_")
info_val <- chemins_trouves$info[i]
df <- tryCatch({
read_delim(path, delim = ",", show_col_types = FALSE)
}, error = function(e) {
warning(paste("Erreur lors de l'import:", path))
return(NULL)
})
if (!is.null(df)) {
df$ID <- id_label
df$Info <- info_val
df_2 <- subset(df,padj < 0.05 & abs(log2FoldChange) > 1 & padj != 0)
#use subset to filter dataframes by columns
list_tables[[length(list_tables) + 1]] <- df_2
}
}## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## • `` -> `...1`# Fusionner tous les tableaux
table_fusionnee <- bind_rows(list_tables)
colnames(table_fusionnee)[1] <- "gene_id"
# Aperçu ou sauvegarde
print(head(table_fusionnee))## # A tibble: 6 × 9
## gene_id baseMean log2FoldChange lfcSE stat pvalue padj ID Info
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 lcl|NC_092… 134. -20.7 1.54 -13.4 4.49e-41 1.03e-36 B_t1… Inse…
## 2 lcl|NC_092… 17.9 -18.3 2.04 -8.98 2.64e-19 3.04e-15 B_t1… Inse…
## 3 lcl|NC_092… 76.1 -19.2 2.30 -8.32 8.53e-17 6.55e-13 B_t1… Inse…
## 4 lcl|NC_092… 43.0 22.9 2.76 8.28 1.27e-16 7.30e-13 B_t1… Inse…
## 5 lcl|NC_092… 36.6 -20.2 2.59 -7.79 6.45e-15 2.97e-11 B_t1… Inse…
## 6 lcl|NC_092… 59.8 22.6 3.03 7.47 7.83e-14 3.01e-10 B_t1… Inse…#write_csv(table_fusionnee, "TopGO/Insect/table_fusionnee.csv")
# Vérifier le nombre de gènes significatifs
cat('Nombre de gènes différentiellement exprimés :',
nrow(table_fusionnee), '\\n')## Nombre de gènes différentiellement exprimés : 4953 \n# Renommer les colonnes du fichier interproscan
colnames(interproscan)[1:2] <- c('GeneID', 'GO')
# Supprimer les lignes sans GO
interproscan <- interproscan[!is.na(interproscan$GO) & interproscan$GO != '', ]
# Associer chaque gène à ses termes GO
gene2GO <- split(interproscan$GO, interproscan$GeneID)
gene2GO <- lapply(gene2GO, function(x) unique(unlist(strsplit(x, ';'))))
# Définir l'univers des gènes et la liste binaire des gènes significatifs
geneUniverse <- names(gene2GO)
ont_list=c("BP", "MF", "CC")
#BP = Biological Process, MF = Molecular Function, CC = Cellular Component2.2.2 Formalisations des données, tests et représentations graphiques
for (i in unique(table_fusionnee$ID)){
table_trimmed = subset(table_fusionnee, ID == i)
up_table = subset(table_trimmed, log2FoldChange >= 1)
down_table = subset(table_trimmed, log2FoldChange <= -1)
geneList_up <- factor(as.integer(geneUniverse %in% up_table$gene_id),
levels = c(0, 1))
geneList_down <- factor(as.integer(geneUniverse %in% down_table$gene_id),
levels = c(0, 1))
for (y in ont_list){
condition = i
orga = table_fusionnee$Info[i]
ontology = y
names(geneList_up) <- geneUniverse
names(geneList_down) <- geneUniverse
# Création des objets topGO
GOdata_up <- new('topGOdata',
description = "Enrichment analysis",
ontology = y,
allGenes = geneList_up,
annot = annFUN.gene2GO,
geneSelectionFun = function(x) x == 1,
gene2GO = gene2GO,
nodeSize = 5)
GOdata_down <- new('topGOdata',
description = "Enrichment analysis",
ontology = y,
allGenes = geneList_down,
annot = annFUN.gene2GO,
geneSelectionFun = function(x) x == 1,
gene2GO = gene2GO,
nodeSize = 5)
# UP
resultFisher_up_w01 <- runTest(GOdata_up, algorithm = 'weight01',
statistic = 'fisher')
resultFisher_up_classic <- runTest(GOdata_up, algorithm = 'classic',
statistic = 'fisher')
GOtable_up <- GenTable(GOdata_up, p.value = resultFisher_up_w01,
orderBy = 'p.value', topNodes = 20)
GOtable_up
# write.csv(GOtable_up, paste0('TopGO/Insect/TopGO_Down/topGO_results_up_',
# i, '_', y, '.csv'), row.names = FALSE)
allRes <- GenTable(GOdata_down, classic = resultFisher_up_classic,
weight = resultFisher_up_w01, orderBy = "weight",
ranksOf = "weight", topNodes = 20)
knitr::kable(allRes)
# GO.res <-
showSigOfNodes(GOdata_up, score(resultFisher_up_classic),
firstSigNodes = 20, useInfo = 'all')
# DOWN
resultFisher_down_w01 <- runTest(GOdata_down, algorithm = 'weight01',
statistic = 'fisher')
resultFisher_down_classic <- runTest(GOdata_down, algorithm = 'classic',
statistic = 'fisher')
GOtable_down <- GenTable(GOdata_down, p.value = resultFisher_down_w01,
orderBy = 'p.value', topNodes = 20)
GOtable_down
# write.csv(GOtable_down, paste0('TopGO/Insect/TopGO_Up/topGO_results_down_',
# i, '_', y, '.csv'), row.names = FALSE)
# FILTRER p.value
GOtable_up_filt <- GOtable_up[as.numeric(GOtable_up$p.value) < 0.05, ]
GOtable_down_filt <- GOtable_down[as.numeric(GOtable_down$p.value) < 0.05, ]
if (nrow(GOtable_up_filt) == 0 && nrow(GOtable_down_filt) == 0) {
next # passer à la prochaine itération du for(y in ont_list)
}
# Ajouter colonne Direction et inv_pvalue
if (nrow(GOtable_up_filt) > 0) {
GOtable_up_filt$Direction <- "Up"
GOtable_up_filt$p.value <- as.numeric(GOtable_up_filt$p.value)
GOtable_up_filt$inv_pvalue <- GOtable_up_filt$p.value
}
if (nrow(GOtable_down_filt) > 0) {
GOtable_down_filt$Direction <- "Down"
GOtable_down_filt$p.value <- as.numeric(GOtable_down_filt$p.value)
GOtable_down_filt$inv_pvalue <- 1 / GOtable_down_filt$p.value
}
# Fusionner uniquement ceux qui existent
GOtable_filt <- rbind(
if (exists("GOtable_up_filt")) GOtable_up_filt else NULL,
if (exists("GOtable_down_filt")) GOtable_down_filt else NULL
)
# Tracer
g <- ggplot(GOtable_filt, aes(x = reorder(Term, -log10(
as.numeric(inv_pvalue))),
y = -log10(as.numeric(inv_pvalue)))) +
geom_bar(stat = 'identity', fill = '#00a3a6') +
geom_hline(yintercept = -log10(0.05), color = 'red', linetype =
'dashed', linewidth = 1) +
geom_hline(yintercept = -log10(1 / 0.05), color = 'red', linetype =
'dashed', linewidth = 1) +
geom_hline(yintercept = 0, color = 'white', linewidth = 0.5) +
coord_flip() +
labs(x = 'Termes GO', y = '-log10[p-value]', title = i)
print(g)
# ggsave(paste0("TopGO/Insect/topGO_results_", i, '_', y, '.pdf'), plot = g)
allRes <- GenTable(GOdata_down, classic = resultFisher_down_classic,
weight = resultFisher_down_w01, orderBy = "weight",
ranksOf = "weight", topNodes = 20)
knitr::kable(allRes)
# GO.res <-
showSigOfNodes(GOdata_down, topGO::score(resultFisher_down_classic),
firstSigNodes = 20, useInfo = 'all')
}
}##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 114 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 6 nodes to be scored (32 eliminated genes)##
## Level 8: 11 nodes to be scored (60 eliminated genes)##
## Level 7: 15 nodes to be scored (1941 eliminated genes)##
## Level 6: 17 nodes to be scored (2528 eliminated genes)##
## Level 5: 24 nodes to be scored (4997 eliminated genes)##
## Level 4: 17 nodes to be scored (7451 eliminated genes)##
## Level 3: 12 nodes to be scored (14850 eliminated genes)##
## Level 2: 5 nodes to be scored (16498 eliminated genes)##
## Level 1: 1 nodes to be scored (17440 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 114 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 109 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 3 nodes to be scored (34 eliminated genes)##
## Level 10: 6 nodes to be scored (34 eliminated genes)##
## Level 9: 8 nodes to be scored (34 eliminated genes)##
## Level 8: 12 nodes to be scored (49 eliminated genes)##
## Level 7: 15 nodes to be scored (2000 eliminated genes)##
## Level 6: 14 nodes to be scored (2657 eliminated genes)##
## Level 5: 18 nodes to be scored (4483 eliminated genes)##
## Level 4: 14 nodes to be scored (5156 eliminated genes)##
## Level 3: 11 nodes to be scored (10839 eliminated genes)##
## Level 2: 5 nodes to be scored (15518 eliminated genes)##
## Level 1: 1 nodes to be scored (17726 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 109 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 92 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 5 nodes to be scored (78 eliminated genes)##
## Level 7: 9 nodes to be scored (3502 eliminated genes)##
## Level 6: 14 nodes to be scored (4712 eliminated genes)##
## Level 5: 22 nodes to be scored (6521 eliminated genes)##
## Level 4: 17 nodes to be scored (8423 eliminated genes)##
## Level 3: 12 nodes to be scored (14091 eliminated genes)##
## Level 2: 8 nodes to be scored (15721 eliminated genes)##
## Level 1: 1 nodes to be scored (26485 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 92 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 75 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 8 nodes to be scored (3820 eliminated genes)##
## Level 6: 10 nodes to be scored (5069 eliminated genes)##
## Level 5: 13 nodes to be scored (5940 eliminated genes)##
## Level 4: 16 nodes to be scored (8158 eliminated genes)##
## Level 3: 13 nodes to be scored (11373 eliminated genes)##
## Level 2: 6 nodes to be scored (14441 eliminated genes)##
## Level 1: 1 nodes to be scored (23404 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 75 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 22 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 2 nodes to be scored (0 eliminated genes)##
## Level 7: 2 nodes to be scored (78 eliminated genes)##
## Level 6: 2 nodes to be scored (250 eliminated genes)##
## Level 5: 3 nodes to be scored (433 eliminated genes)##
## Level 4: 4 nodes to be scored (800 eliminated genes)##
## Level 3: 5 nodes to be scored (2002 eliminated genes)##
## Level 2: 2 nodes to be scored (4191 eliminated genes)##
## Level 1: 1 nodes to be scored (9434 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 22 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 4 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 3: 2 nodes to be scored (0 eliminated genes)##
## Level 2: 1 nodes to be scored (0 eliminated genes)##
## Level 1: 1 nodes to be scored (5993 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 4 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 92 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 2 nodes to be scored (0 eliminated genes)##
## Level 12: 3 nodes to be scored (0 eliminated genes)##
## Level 11: 3 nodes to be scored (22 eliminated genes)##
## Level 10: 4 nodes to be scored (30 eliminated genes)##
## Level 9: 4 nodes to be scored (44 eliminated genes)##
## Level 8: 6 nodes to be scored (89 eliminated genes)##
## Level 7: 10 nodes to be scored (2025 eliminated genes)##
## Level 6: 12 nodes to be scored (3010 eliminated genes)##
## Level 5: 16 nodes to be scored (5359 eliminated genes)##
## Level 4: 15 nodes to be scored (6682 eliminated genes)##
## Level 3: 11 nodes to be scored (12757 eliminated genes)##
## Level 2: 5 nodes to be scored (17446 eliminated genes)##
## Level 1: 1 nodes to be scored (18551 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 92 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 80 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (0 eliminated genes)##
## Level 9: 4 nodes to be scored (12 eliminated genes)##
## Level 8: 8 nodes to be scored (362 eliminated genes)##
## Level 7: 8 nodes to be scored (1806 eliminated genes)##
## Level 6: 9 nodes to be scored (2369 eliminated genes)##
## Level 5: 16 nodes to be scored (3293 eliminated genes)##
## Level 4: 13 nodes to be scored (5294 eliminated genes)##
## Level 3: 12 nodes to be scored (12809 eliminated genes)##
## Level 2: 5 nodes to be scored (15685 eliminated genes)##
## Level 1: 1 nodes to be scored (17734 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 80 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 71 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 9 nodes to be scored (3280 eliminated genes)##
## Level 6: 12 nodes to be scored (3402 eliminated genes)##
## Level 5: 14 nodes to be scored (4247 eliminated genes)##
## Level 4: 13 nodes to be scored (4860 eliminated genes)##
## Level 3: 12 nodes to be scored (12510 eliminated genes)##
## Level 2: 5 nodes to be scored (14235 eliminated genes)##
## Level 1: 1 nodes to be scored (25725 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 71 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 94 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 5 nodes to be scored (0 eliminated genes)##
## Level 7: 7 nodes to be scored (3854 eliminated genes)##
## Level 6: 15 nodes to be scored (4998 eliminated genes)##
## Level 5: 20 nodes to be scored (5981 eliminated genes)##
## Level 4: 19 nodes to be scored (8169 eliminated genes)##
## Level 3: 15 nodes to be scored (12994 eliminated genes)##
## Level 2: 9 nodes to be scored (14620 eliminated genes)##
## Level 1: 1 nodes to be scored (24381 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 94 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 12 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 1 nodes to be scored (170 eliminated genes)##
## Level 5: 1 nodes to be scored (260 eliminated genes)##
## Level 4: 2 nodes to be scored (627 eliminated genes)##
## Level 3: 3 nodes to be scored (1674 eliminated genes)##
## Level 2: 2 nodes to be scored (3535 eliminated genes)##
## Level 1: 1 nodes to be scored (9420 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 12 nontrivial nodes
## parameters:
## test statistic: fisher## Warning in arrows(head_from[1], head_from[2], head_to[1], head_to[2], col =
## edgeColor, : zero-length arrow is of indeterminate angle and so skipped
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 18 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 2 nodes to be scored (0 eliminated genes)##
## Level 6: 3 nodes to be scored (170 eliminated genes)##
## Level 5: 2 nodes to be scored (308 eliminated genes)##
## Level 4: 4 nodes to be scored (2012 eliminated genes)##
## Level 3: 3 nodes to be scored (3534 eliminated genes)##
## Level 2: 2 nodes to be scored (4148 eliminated genes)##
## Level 1: 1 nodes to be scored (9420 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 18 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 92 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (0 eliminated genes)##
## Level 9: 6 nodes to be scored (22 eliminated genes)##
## Level 8: 6 nodes to be scored (64 eliminated genes)##
## Level 7: 13 nodes to be scored (1827 eliminated genes)##
## Level 6: 15 nodes to be scored (2351 eliminated genes)##
## Level 5: 18 nodes to be scored (4745 eliminated genes)##
## Level 4: 16 nodes to be scored (7372 eliminated genes)##
## Level 3: 9 nodes to be scored (11030 eliminated genes)##
## Level 2: 4 nodes to be scored (14312 eliminated genes)##
## Level 1: 1 nodes to be scored (14896 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 92 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 105 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 9 nodes to be scored (47 eliminated genes)##
## Level 8: 10 nodes to be scored (513 eliminated genes)##
## Level 7: 11 nodes to be scored (2167 eliminated genes)##
## Level 6: 15 nodes to be scored (2648 eliminated genes)##
## Level 5: 19 nodes to be scored (3593 eliminated genes)##
## Level 4: 15 nodes to be scored (5897 eliminated genes)##
## Level 3: 15 nodes to be scored (14223 eliminated genes)##
## Level 2: 5 nodes to be scored (16391 eliminated genes)##
## Level 1: 1 nodes to be scored (18644 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 105 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 63 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 2 nodes to be scored (0 eliminated genes)##
## Level 7: 5 nodes to be scored (3268 eliminated genes)##
## Level 6: 9 nodes to be scored (3318 eliminated genes)##
## Level 5: 13 nodes to be scored (4075 eliminated genes)##
## Level 4: 15 nodes to be scored (4305 eliminated genes)##
## Level 3: 11 nodes to be scored (9590 eliminated genes)##
## Level 2: 6 nodes to be scored (13844 eliminated genes)##
## Level 1: 1 nodes to be scored (23430 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 63 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 44 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 6 nodes to be scored (16 eliminated genes)##
## Level 5: 9 nodes to be scored (16 eliminated genes)##
## Level 4: 9 nodes to be scored (1014 eliminated genes)##
## Level 3: 11 nodes to be scored (4984 eliminated genes)##
## Level 2: 6 nodes to be scored (6464 eliminated genes)##
## Level 1: 1 nodes to be scored (23228 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 44 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 9 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 6: 1 nodes to be scored (0 eliminated genes)##
## Level 5: 1 nodes to be scored (0 eliminated genes)##
## Level 4: 2 nodes to be scored (1337 eliminated genes)##
## Level 3: 3 nodes to be scored (2126 eliminated genes)##
## Level 2: 1 nodes to be scored (3564 eliminated genes)##
## Level 1: 1 nodes to be scored (4496 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 9 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 5 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 4: 1 nodes to be scored (0 eliminated genes)##
## Level 3: 2 nodes to be scored (0 eliminated genes)##
## Level 2: 1 nodes to be scored (549 eliminated genes)##
## Level 1: 1 nodes to be scored (5756 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 5 nontrivial nodes
## parameters:
## test statistic: fisher##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 126 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 5 nodes to be scored (0 eliminated genes)##
## Level 9: 10 nodes to be scored (22 eliminated genes)##
## Level 8: 15 nodes to be scored (78 eliminated genes)##
## Level 7: 19 nodes to be scored (2306 eliminated genes)##
## Level 6: 16 nodes to be scored (4095 eliminated genes)##
## Level 5: 22 nodes to be scored (7006 eliminated genes)##
## Level 4: 17 nodes to be scored (8983 eliminated genes)##
## Level 3: 14 nodes to be scored (15235 eliminated genes)##
## Level 2: 6 nodes to be scored (17025 eliminated genes)##
## Level 1: 1 nodes to be scored (18559 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 126 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 52 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 4 nodes to be scored (0 eliminated genes)##
## Level 8: 5 nodes to be scored (341 eliminated genes)##
## Level 7: 7 nodes to be scored (1960 eliminated genes)##
## Level 6: 7 nodes to be scored (2356 eliminated genes)##
## Level 5: 10 nodes to be scored (3934 eliminated genes)##
## Level 4: 7 nodes to be scored (5096 eliminated genes)##
## Level 3: 6 nodes to be scored (7973 eliminated genes)##
## Level 2: 3 nodes to be scored (12800 eliminated genes)##
## Level 1: 1 nodes to be scored (14854 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 52 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 135 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 4 nodes to be scored (0 eliminated genes)##
## Level 8: 9 nodes to be scored (78 eliminated genes)##
## Level 7: 16 nodes to be scored (3500 eliminated genes)##
## Level 6: 26 nodes to be scored (4997 eliminated genes)##
## Level 5: 30 nodes to be scored (6820 eliminated genes)##
## Level 4: 25 nodes to be scored (9636 eliminated genes)##
## Level 3: 15 nodes to be scored (15707 eliminated genes)##
## Level 2: 8 nodes to be scored (17876 eliminated genes)##
## Level 1: 1 nodes to be scored (26575 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 135 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 80 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 5 nodes to be scored (40 eliminated genes)##
## Level 7: 8 nodes to be scored (3310 eliminated genes)##
## Level 6: 13 nodes to be scored (4547 eliminated genes)##
## Level 5: 15 nodes to be scored (6068 eliminated genes)##
## Level 4: 16 nodes to be scored (8635 eliminated genes)##
## Level 3: 12 nodes to be scored (12865 eliminated genes)##
## Level 2: 7 nodes to be scored (15023 eliminated genes)##
## Level 1: 1 nodes to be scored (25210 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 80 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 31 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 4 nodes to be scored (104 eliminated genes)##
## Level 6: 4 nodes to be scored (310 eliminated genes)##
## Level 5: 4 nodes to be scored (669 eliminated genes)##
## Level 4: 6 nodes to be scored (1394 eliminated genes)##
## Level 3: 5 nodes to be scored (3794 eliminated genes)##
## Level 2: 2 nodes to be scored (4768 eliminated genes)##
## Level 1: 1 nodes to be scored (9434 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 31 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 20 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 1 nodes to be scored (0 eliminated genes)##
## Level 6: 3 nodes to be scored (66 eliminated genes)##
## Level 5: 3 nodes to be scored (286 eliminated genes)##
## Level 4: 5 nodes to be scored (1585 eliminated genes)##
## Level 3: 4 nodes to be scored (3540 eliminated genes)##
## Level 2: 2 nodes to be scored (4252 eliminated genes)##
## Level 1: 1 nodes to be scored (4562 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 20 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 311 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 2 nodes to be scored (0 eliminated genes)##
## Level 11: 5 nodes to be scored (0 eliminated genes)##
## Level 10: 20 nodes to be scored (79 eliminated genes)##
## Level 9: 24 nodes to be scored (125 eliminated genes)##
## Level 8: 39 nodes to be scored (538 eliminated genes)##
## Level 7: 52 nodes to be scored (3021 eliminated genes)##
## Level 6: 44 nodes to be scored (4604 eliminated genes)##
## Level 5: 53 nodes to be scored (8935 eliminated genes)##
## Level 4: 39 nodes to be scored (11122 eliminated genes)##
## Level 3: 25 nodes to be scored (15914 eliminated genes)##
## Level 2: 7 nodes to be scored (18281 eliminated genes)##
## Level 1: 1 nodes to be scored (18808 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 311 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 315 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 3 nodes to be scored (0 eliminated genes)##
## Level 12: 4 nodes to be scored (117 eliminated genes)##
## Level 11: 6 nodes to be scored (131 eliminated genes)##
## Level 10: 14 nodes to be scored (135 eliminated genes)##
## Level 9: 22 nodes to be scored (191 eliminated genes)##
## Level 8: 40 nodes to be scored (331 eliminated genes)##
## Level 7: 48 nodes to be scored (3061 eliminated genes)##
## Level 6: 45 nodes to be scored (5746 eliminated genes)##
## Level 5: 57 nodes to be scored (9181 eliminated genes)##
## Level 4: 37 nodes to be scored (11862 eliminated genes)##
## Level 3: 28 nodes to be scored (16526 eliminated genes)##
## Level 2: 9 nodes to be scored (18170 eliminated genes)##
## Level 1: 1 nodes to be scored (18694 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 315 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 282 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 5 nodes to be scored (0 eliminated genes)##
## Level 8: 12 nodes to be scored (14 eliminated genes)##
## Level 7: 38 nodes to be scored (3948 eliminated genes)##
## Level 6: 59 nodes to be scored (6030 eliminated genes)##
## Level 5: 69 nodes to be scored (7878 eliminated genes)##
## Level 4: 54 nodes to be scored (10572 eliminated genes)##
## Level 3: 28 nodes to be scored (17385 eliminated genes)##
## Level 2: 15 nodes to be scored (20641 eliminated genes)##
## Level 1: 1 nodes to be scored (27660 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 282 nontrivial nodes
## parameters:
## test statistic: fisher## Warning in arrows(head_from[1], head_from[2], head_to[1], head_to[2], col =
## edgeColor, : zero-length arrow is of indeterminate angle and so skipped
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 267 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (0 eliminated genes)##
## Level 9: 10 nodes to be scored (22 eliminated genes)##
## Level 8: 17 nodes to be scored (214 eliminated genes)##
## Level 7: 32 nodes to be scored (4335 eliminated genes)##
## Level 6: 55 nodes to be scored (6399 eliminated genes)##
## Level 5: 59 nodes to be scored (8030 eliminated genes)##
## Level 4: 51 nodes to be scored (11752 eliminated genes)##
## Level 3: 25 nodes to be scored (17542 eliminated genes)##
## Level 2: 13 nodes to be scored (19531 eliminated genes)##
## Level 1: 1 nodes to be scored (28045 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 267 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 76 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 6 nodes to be scored (0 eliminated genes)##
## Level 8: 10 nodes to be scored (106 eliminated genes)##
## Level 7: 10 nodes to be scored (154 eliminated genes)##
## Level 6: 12 nodes to be scored (654 eliminated genes)##
## Level 5: 9 nodes to be scored (1529 eliminated genes)##
## Level 4: 11 nodes to be scored (3255 eliminated genes)##
## Level 3: 13 nodes to be scored (3818 eliminated genes)##
## Level 2: 2 nodes to be scored (4608 eliminated genes)##
## Level 1: 1 nodes to be scored (10032 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 76 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 42 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 2 nodes to be scored (0 eliminated genes)##
## Level 7: 4 nodes to be scored (114 eliminated genes)##
## Level 6: 7 nodes to be scored (180 eliminated genes)##
## Level 5: 6 nodes to be scored (859 eliminated genes)##
## Level 4: 8 nodes to be scored (2988 eliminated genes)##
## Level 3: 9 nodes to be scored (3889 eliminated genes)##
## Level 2: 2 nodes to be scored (4872 eliminated genes)##
## Level 1: 1 nodes to be scored (10032 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 42 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 314 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 2 nodes to be scored (0 eliminated genes)##
## Level 12: 2 nodes to be scored (117 eliminated genes)##
## Level 11: 6 nodes to be scored (117 eliminated genes)##
## Level 10: 17 nodes to be scored (117 eliminated genes)##
## Level 9: 23 nodes to be scored (306 eliminated genes)##
## Level 8: 33 nodes to be scored (809 eliminated genes)##
## Level 7: 47 nodes to be scored (3331 eliminated genes)##
## Level 6: 44 nodes to be scored (5229 eliminated genes)##
## Level 5: 56 nodes to be scored (8974 eliminated genes)##
## Level 4: 40 nodes to be scored (11408 eliminated genes)##
## Level 3: 33 nodes to be scored (15834 eliminated genes)##
## Level 2: 9 nodes to be scored (18021 eliminated genes)##
## Level 1: 1 nodes to be scored (18995 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 314 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 159 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 2 nodes to be scored (0 eliminated genes)##
## Level 11: 1 nodes to be scored (14 eliminated genes)##
## Level 10: 3 nodes to be scored (18 eliminated genes)##
## Level 9: 5 nodes to be scored (18 eliminated genes)##
## Level 8: 15 nodes to be scored (385 eliminated genes)##
## Level 7: 25 nodes to be scored (1884 eliminated genes)##
## Level 6: 31 nodes to be scored (3323 eliminated genes)##
## Level 5: 32 nodes to be scored (5836 eliminated genes)##
## Level 4: 22 nodes to be scored (9931 eliminated genes)##
## Level 3: 16 nodes to be scored (15972 eliminated genes)##
## Level 2: 5 nodes to be scored (18028 eliminated genes)##
## Level 1: 1 nodes to be scored (18713 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 159 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 225 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 9 nodes to be scored (22 eliminated genes)##
## Level 8: 17 nodes to be scored (200 eliminated genes)##
## Level 7: 33 nodes to be scored (4286 eliminated genes)##
## Level 6: 44 nodes to be scored (6547 eliminated genes)##
## Level 5: 47 nodes to be scored (7894 eliminated genes)##
## Level 4: 39 nodes to be scored (10910 eliminated genes)##
## Level 3: 21 nodes to be scored (17663 eliminated genes)##
## Level 2: 11 nodes to be scored (19909 eliminated genes)##
## Level 1: 1 nodes to be scored (27306 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 225 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 148 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (0 eliminated genes)##
## Level 8: 10 nodes to be scored (152 eliminated genes)##
## Level 7: 19 nodes to be scored (3735 eliminated genes)##
## Level 6: 24 nodes to be scored (5232 eliminated genes)##
## Level 5: 28 nodes to be scored (7569 eliminated genes)##
## Level 4: 29 nodes to be scored (9377 eliminated genes)##
## Level 3: 18 nodes to be scored (16130 eliminated genes)##
## Level 2: 10 nodes to be scored (18596 eliminated genes)##
## Level 1: 1 nodes to be scored (26769 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 148 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 61 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 5 nodes to be scored (6 eliminated genes)##
## Level 8: 7 nodes to be scored (62 eliminated genes)##
## Level 7: 8 nodes to be scored (186 eliminated genes)##
## Level 6: 7 nodes to be scored (442 eliminated genes)##
## Level 5: 8 nodes to be scored (891 eliminated genes)##
## Level 4: 10 nodes to be scored (2463 eliminated genes)##
## Level 3: 10 nodes to be scored (3874 eliminated genes)##
## Level 2: 2 nodes to be scored (4897 eliminated genes)##
## Level 1: 1 nodes to be scored (9957 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 61 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 4 nodes to be scored (0 eliminated genes)##
## Level 6: 6 nodes to be scored (350 eliminated genes)##
## Level 5: 4 nodes to be scored (978 eliminated genes)##
## Level 4: 6 nodes to be scored (2578 eliminated genes)##
## Level 3: 9 nodes to be scored (3540 eliminated genes)##
## Level 2: 2 nodes to be scored (4691 eliminated genes)##
## Level 1: 1 nodes to be scored (9987 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 289 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 4 nodes to be scored (0 eliminated genes)##
## Level 10: 14 nodes to be scored (0 eliminated genes)##
## Level 9: 20 nodes to be scored (91 eliminated genes)##
## Level 8: 31 nodes to be scored (631 eliminated genes)##
## Level 7: 43 nodes to be scored (2926 eliminated genes)##
## Level 6: 41 nodes to be scored (4425 eliminated genes)##
## Level 5: 55 nodes to be scored (7891 eliminated genes)##
## Level 4: 41 nodes to be scored (10793 eliminated genes)##
## Level 3: 31 nodes to be scored (16514 eliminated genes)##
## Level 2: 8 nodes to be scored (18414 eliminated genes)##
## Level 1: 1 nodes to be scored (19018 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 289 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 343 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 2 nodes to be scored (0 eliminated genes)##
## Level 12: 4 nodes to be scored (0 eliminated genes)##
## Level 11: 7 nodes to be scored (48 eliminated genes)##
## Level 10: 14 nodes to be scored (113 eliminated genes)##
## Level 9: 25 nodes to be scored (144 eliminated genes)##
## Level 8: 42 nodes to be scored (551 eliminated genes)##
## Level 7: 58 nodes to be scored (2907 eliminated genes)##
## Level 6: 52 nodes to be scored (5200 eliminated genes)##
## Level 5: 57 nodes to be scored (9430 eliminated genes)##
## Level 4: 43 nodes to be scored (11947 eliminated genes)##
## Level 3: 30 nodes to be scored (16823 eliminated genes)##
## Level 2: 8 nodes to be scored (18460 eliminated genes)##
## Level 1: 1 nodes to be scored (18949 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 343 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 237 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 11 nodes to be scored (0 eliminated genes)##
## Level 7: 27 nodes to be scored (3853 eliminated genes)##
## Level 6: 52 nodes to be scored (5850 eliminated genes)##
## Level 5: 59 nodes to be scored (7511 eliminated genes)##
## Level 4: 42 nodes to be scored (10595 eliminated genes)##
## Level 3: 28 nodes to be scored (17236 eliminated genes)##
## Level 2: 14 nodes to be scored (19418 eliminated genes)##
## Level 1: 1 nodes to be scored (27778 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 237 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 252 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 7 nodes to be scored (0 eliminated genes)##
## Level 8: 17 nodes to be scored (0 eliminated genes)##
## Level 7: 31 nodes to be scored (4069 eliminated genes)##
## Level 6: 51 nodes to be scored (6272 eliminated genes)##
## Level 5: 58 nodes to be scored (8136 eliminated genes)##
## Level 4: 48 nodes to be scored (11506 eliminated genes)##
## Level 3: 26 nodes to be scored (17884 eliminated genes)##
## Level 2: 13 nodes to be scored (19773 eliminated genes)##
## Level 1: 1 nodes to be scored (27878 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 252 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 49 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (68 eliminated genes)##
## Level 7: 6 nodes to be scored (124 eliminated genes)##
## Level 6: 6 nodes to be scored (435 eliminated genes)##
## Level 5: 5 nodes to be scored (1072 eliminated genes)##
## Level 4: 8 nodes to be scored (2767 eliminated genes)##
## Level 3: 10 nodes to be scored (3564 eliminated genes)##
## Level 2: 2 nodes to be scored (4783 eliminated genes)##
## Level 1: 1 nodes to be scored (10032 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 49 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 49 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 4 nodes to be scored (0 eliminated genes)##
## Level 7: 6 nodes to be scored (22 eliminated genes)##
## Level 6: 9 nodes to be scored (215 eliminated genes)##
## Level 5: 7 nodes to be scored (602 eliminated genes)##
## Level 4: 8 nodes to be scored (3043 eliminated genes)##
## Level 3: 11 nodes to be scored (3875 eliminated genes)##
## Level 2: 2 nodes to be scored (4916 eliminated genes)##
## Level 1: 1 nodes to be scored (10032 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 49 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 226 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 1 nodes to be scored (0 eliminated genes)##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 4 nodes to be scored (8 eliminated genes)##
## Level 10: 15 nodes to be scored (12 eliminated genes)##
## Level 9: 17 nodes to be scored (48 eliminated genes)##
## Level 8: 23 nodes to be scored (556 eliminated genes)##
## Level 7: 34 nodes to be scored (2632 eliminated genes)##
## Level 6: 33 nodes to be scored (3646 eliminated genes)##
## Level 5: 42 nodes to be scored (7256 eliminated genes)##
## Level 4: 30 nodes to be scored (9459 eliminated genes)##
## Level 3: 20 nodes to be scored (15390 eliminated genes)##
## Level 2: 5 nodes to be scored (17954 eliminated genes)##
## Level 1: 1 nodes to be scored (18644 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 226 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 206 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 2 nodes to be scored (0 eliminated genes)##
## Level 12: 2 nodes to be scored (117 eliminated genes)##
## Level 11: 4 nodes to be scored (117 eliminated genes)##
## Level 10: 8 nodes to be scored (117 eliminated genes)##
## Level 9: 13 nodes to be scored (186 eliminated genes)##
## Level 8: 21 nodes to be scored (691 eliminated genes)##
## Level 7: 30 nodes to be scored (2717 eliminated genes)##
## Level 6: 29 nodes to be scored (3740 eliminated genes)##
## Level 5: 34 nodes to be scored (7482 eliminated genes)##
## Level 4: 30 nodes to be scored (9886 eliminated genes)##
## Level 3: 23 nodes to be scored (16111 eliminated genes)##
## Level 2: 8 nodes to be scored (17879 eliminated genes)##
## Level 1: 1 nodes to be scored (18790 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 206 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 193 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 9 nodes to be scored (40 eliminated genes)##
## Level 7: 23 nodes to be scored (3320 eliminated genes)##
## Level 6: 37 nodes to be scored (5317 eliminated genes)##
## Level 5: 45 nodes to be scored (7419 eliminated genes)##
## Level 4: 44 nodes to be scored (10365 eliminated genes)##
## Level 3: 20 nodes to be scored (16885 eliminated genes)##
## Level 2: 10 nodes to be scored (19825 eliminated genes)##
## Level 1: 1 nodes to be scored (27146 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 193 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 179 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 3 nodes to be scored (0 eliminated genes)##
## Level 9: 5 nodes to be scored (74 eliminated genes)##
## Level 8: 13 nodes to be scored (306 eliminated genes)##
## Level 7: 16 nodes to be scored (4246 eliminated genes)##
## Level 6: 28 nodes to be scored (6188 eliminated genes)##
## Level 5: 39 nodes to be scored (7386 eliminated genes)##
## Level 4: 41 nodes to be scored (9498 eliminated genes)##
## Level 3: 22 nodes to be scored (15571 eliminated genes)##
## Level 2: 10 nodes to be scored (18761 eliminated genes)##
## Level 1: 1 nodes to be scored (27303 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 179 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 46 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 7 nodes to be scored (56 eliminated genes)##
## Level 7: 5 nodes to be scored (72 eliminated genes)##
## Level 6: 5 nodes to be scored (386 eliminated genes)##
## Level 5: 6 nodes to be scored (734 eliminated genes)##
## Level 4: 8 nodes to be scored (2212 eliminated genes)##
## Level 3: 9 nodes to be scored (3586 eliminated genes)##
## Level 2: 2 nodes to be scored (4279 eliminated genes)##
## Level 1: 1 nodes to be scored (9957 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 46 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 4 nodes to be scored (0 eliminated genes)##
## Level 7: 5 nodes to be scored (108 eliminated genes)##
## Level 6: 5 nodes to be scored (398 eliminated genes)##
## Level 5: 4 nodes to be scored (781 eliminated genes)##
## Level 4: 6 nodes to be scored (2427 eliminated genes)##
## Level 3: 6 nodes to be scored (3794 eliminated genes)##
## Level 2: 2 nodes to be scored (4768 eliminated genes)##
## Level 1: 1 nodes to be scored (9434 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 35 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 341 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 3 nodes to be scored (0 eliminated genes)##
## Level 11: 7 nodes to be scored (0 eliminated genes)##
## Level 10: 24 nodes to be scored (84 eliminated genes)##
## Level 9: 29 nodes to be scored (148 eliminated genes)##
## Level 8: 42 nodes to be scored (937 eliminated genes)##
## Level 7: 51 nodes to be scored (2967 eliminated genes)##
## Level 6: 44 nodes to be scored (4569 eliminated genes)##
## Level 5: 57 nodes to be scored (7322 eliminated genes)##
## Level 4: 43 nodes to be scored (8906 eliminated genes)##
## Level 3: 31 nodes to be scored (16664 eliminated genes)##
## Level 2: 9 nodes to be scored (18379 eliminated genes)##
## Level 1: 1 nodes to be scored (18969 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 341 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 435 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 13: 3 nodes to be scored (0 eliminated genes)##
## Level 12: 6 nodes to be scored (0 eliminated genes)##
## Level 11: 11 nodes to be scored (56 eliminated genes)##
## Level 10: 33 nodes to be scored (207 eliminated genes)##
## Level 9: 44 nodes to be scored (258 eliminated genes)##
## Level 8: 58 nodes to be scored (750 eliminated genes)##
## Level 7: 68 nodes to be scored (3199 eliminated genes)##
## Level 6: 59 nodes to be scored (5273 eliminated genes)##
## Level 5: 66 nodes to be scored (9101 eliminated genes)##
## Level 4: 47 nodes to be scored (10845 eliminated genes)##
## Level 3: 31 nodes to be scored (16620 eliminated genes)##
## Level 2: 8 nodes to be scored (18355 eliminated genes)##
## Level 1: 1 nodes to be scored (18842 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 435 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 254 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (74 eliminated genes)##
## Level 8: 17 nodes to be scored (184 eliminated genes)##
## Level 7: 26 nodes to be scored (4291 eliminated genes)##
## Level 6: 46 nodes to be scored (6504 eliminated genes)##
## Level 5: 59 nodes to be scored (8195 eliminated genes)##
## Level 4: 55 nodes to be scored (10897 eliminated genes)##
## Level 3: 27 nodes to be scored (17205 eliminated genes)##
## Level 2: 13 nodes to be scored (19826 eliminated genes)##
## Level 1: 1 nodes to be scored (27711 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 254 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 297 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 9 nodes to be scored (22 eliminated genes)##
## Level 8: 19 nodes to be scored (162 eliminated genes)##
## Level 7: 42 nodes to be scored (4347 eliminated genes)##
## Level 6: 61 nodes to be scored (6533 eliminated genes)##
## Level 5: 67 nodes to be scored (8302 eliminated genes)##
## Level 4: 54 nodes to be scored (11643 eliminated genes)##
## Level 3: 26 nodes to be scored (18048 eliminated genes)##
## Level 2: 15 nodes to be scored (20347 eliminated genes)##
## Level 1: 1 nodes to be scored (28047 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 297 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 47 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 6 nodes to be scored (121 eliminated genes)##
## Level 6: 8 nodes to be scored (503 eliminated genes)##
## Level 5: 5 nodes to be scored (873 eliminated genes)##
## Level 4: 6 nodes to be scored (3061 eliminated genes)##
## Level 3: 10 nodes to be scored (3802 eliminated genes)##
## Level 2: 2 nodes to be scored (4768 eliminated genes)##
## Level 1: 1 nodes to be scored (9956 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 47 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 74 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 12 nodes to be scored (0 eliminated genes)##
## Level 7: 12 nodes to be scored (48 eliminated genes)##
## Level 6: 12 nodes to be scored (532 eliminated genes)##
## Level 5: 11 nodes to be scored (1198 eliminated genes)##
## Level 4: 9 nodes to be scored (3395 eliminated genes)##
## Level 3: 12 nodes to be scored (3917 eliminated genes)##
## Level 2: 2 nodes to be scored (4916 eliminated genes)##
## Level 1: 1 nodes to be scored (10032 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 74 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 287 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 2 nodes to be scored (0 eliminated genes)##
## Level 11: 5 nodes to be scored (0 eliminated genes)##
## Level 10: 15 nodes to be scored (79 eliminated genes)##
## Level 9: 22 nodes to be scored (137 eliminated genes)##
## Level 8: 38 nodes to be scored (481 eliminated genes)##
## Level 7: 43 nodes to be scored (2774 eliminated genes)##
## Level 6: 40 nodes to be scored (4652 eliminated genes)##
## Level 5: 50 nodes to be scored (8422 eliminated genes)##
## Level 4: 38 nodes to be scored (11193 eliminated genes)##
## Level 3: 26 nodes to be scored (16291 eliminated genes)##
## Level 2: 7 nodes to be scored (18402 eliminated genes)##
## Level 1: 1 nodes to be scored (18821 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 287 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 366 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 14: 1 nodes to be scored (0 eliminated genes)##
## Level 13: 2 nodes to be scored (0 eliminated genes)##
## Level 12: 3 nodes to be scored (117 eliminated genes)##
## Level 11: 6 nodes to be scored (117 eliminated genes)##
## Level 10: 19 nodes to be scored (199 eliminated genes)##
## Level 9: 29 nodes to be scored (255 eliminated genes)##
## Level 8: 52 nodes to be scored (521 eliminated genes)##
## Level 7: 56 nodes to be scored (3205 eliminated genes)##
## Level 6: 51 nodes to be scored (5602 eliminated genes)##
## Level 5: 61 nodes to be scored (8703 eliminated genes)##
## Level 4: 44 nodes to be scored (10910 eliminated genes)##
## Level 3: 33 nodes to be scored (16771 eliminated genes)##
## Level 2: 8 nodes to be scored (18411 eliminated genes)##
## Level 1: 1 nodes to be scored (19037 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 366 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 233 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 6 nodes to be scored (0 eliminated genes)##
## Level 8: 16 nodes to be scored (0 eliminated genes)##
## Level 7: 27 nodes to be scored (4057 eliminated genes)##
## Level 6: 46 nodes to be scored (6293 eliminated genes)##
## Level 5: 53 nodes to be scored (7523 eliminated genes)##
## Level 4: 47 nodes to be scored (10959 eliminated genes)##
## Level 3: 24 nodes to be scored (17560 eliminated genes)##
## Level 2: 13 nodes to be scored (19817 eliminated genes)##
## Level 1: 1 nodes to be scored (27318 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 233 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 256 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 2 nodes to be scored (0 eliminated genes)##
## Level 9: 7 nodes to be scored (22 eliminated genes)##
## Level 8: 18 nodes to be scored (200 eliminated genes)##
## Level 7: 35 nodes to be scored (4142 eliminated genes)##
## Level 6: 48 nodes to be scored (6392 eliminated genes)##
## Level 5: 62 nodes to be scored (7572 eliminated genes)##
## Level 4: 47 nodes to be scored (11333 eliminated genes)##
## Level 3: 22 nodes to be scored (17814 eliminated genes)##
## Level 2: 13 nodes to be scored (19377 eliminated genes)##
## Level 1: 1 nodes to be scored (28027 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 256 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 49 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 5 nodes to be scored (105 eliminated genes)##
## Level 6: 8 nodes to be scored (345 eliminated genes)##
## Level 5: 6 nodes to be scored (755 eliminated genes)##
## Level 4: 7 nodes to be scored (3013 eliminated genes)##
## Level 3: 11 nodes to be scored (3802 eliminated genes)##
## Level 2: 2 nodes to be scored (4768 eliminated genes)##
## Level 1: 1 nodes to be scored (9956 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 49 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 54 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 8 nodes to be scored (114 eliminated genes)##
## Level 6: 8 nodes to be scored (323 eliminated genes)##
## Level 5: 8 nodes to be scored (1052 eliminated genes)##
## Level 4: 9 nodes to be scored (3197 eliminated genes)##
## Level 3: 9 nodes to be scored (3933 eliminated genes)##
## Level 2: 2 nodes to be scored (4916 eliminated genes)##
## Level 1: 1 nodes to be scored (9765 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 54 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 182 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 4 nodes to be scored (0 eliminated genes)##
## Level 9: 10 nodes to be scored (24 eliminated genes)##
## Level 8: 18 nodes to be scored (116 eliminated genes)##
## Level 7: 28 nodes to be scored (1981 eliminated genes)##
## Level 6: 28 nodes to be scored (3500 eliminated genes)##
## Level 5: 35 nodes to be scored (5836 eliminated genes)##
## Level 4: 28 nodes to be scored (7698 eliminated genes)##
## Level 3: 22 nodes to be scored (14982 eliminated genes)##
## Level 2: 6 nodes to be scored (18043 eliminated genes)##
## Level 1: 1 nodes to be scored (18756 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 182 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 238 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 2 nodes to be scored (0 eliminated genes)##
## Level 10: 10 nodes to be scored (82 eliminated genes)##
## Level 9: 20 nodes to be scored (129 eliminated genes)##
## Level 8: 30 nodes to be scored (354 eliminated genes)##
## Level 7: 34 nodes to be scored (2227 eliminated genes)##
## Level 6: 34 nodes to be scored (4033 eliminated genes)##
## Level 5: 39 nodes to be scored (6734 eliminated genes)##
## Level 4: 36 nodes to be scored (9973 eliminated genes)##
## Level 3: 25 nodes to be scored (16257 eliminated genes)##
## Level 2: 6 nodes to be scored (18314 eliminated genes)##
## Level 1: 1 nodes to be scored (18871 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 238 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 171 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 10 nodes to be scored (40 eliminated genes)##
## Level 7: 15 nodes to be scored (3862 eliminated genes)##
## Level 6: 31 nodes to be scored (5962 eliminated genes)##
## Level 5: 40 nodes to be scored (7281 eliminated genes)##
## Level 4: 42 nodes to be scored (9600 eliminated genes)##
## Level 3: 19 nodes to be scored (15711 eliminated genes)##
## Level 2: 9 nodes to be scored (19239 eliminated genes)##
## Level 1: 1 nodes to be scored (27357 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 171 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 157 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 1 nodes to be scored (0 eliminated genes)##
## Level 8: 6 nodes to be scored (0 eliminated genes)##
## Level 7: 14 nodes to be scored (3268 eliminated genes)##
## Level 6: 28 nodes to be scored (3965 eliminated genes)##
## Level 5: 39 nodes to be scored (6791 eliminated genes)##
## Level 4: 37 nodes to be scored (9670 eliminated genes)##
## Level 3: 21 nodes to be scored (16268 eliminated genes)##
## Level 2: 10 nodes to be scored (18466 eliminated genes)##
## Level 1: 1 nodes to be scored (27442 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 157 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 25 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 2 nodes to be scored (0 eliminated genes)##
## Level 7: 2 nodes to be scored (0 eliminated genes)##
## Level 6: 4 nodes to be scored (78 eliminated genes)##
## Level 5: 3 nodes to be scored (546 eliminated genes)##
## Level 4: 5 nodes to be scored (2212 eliminated genes)##
## Level 3: 6 nodes to be scored (3540 eliminated genes)##
## Level 2: 2 nodes to be scored (4252 eliminated genes)##
## Level 1: 1 nodes to be scored (9943 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 25 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 1 nodes to be scored (0 eliminated genes)##
## Level 7: 3 nodes to be scored (0 eliminated genes)##
## Level 6: 3 nodes to be scored (170 eliminated genes)##
## Level 5: 3 nodes to be scored (313 eliminated genes)##
## Level 4: 5 nodes to be scored (726 eliminated genes)##
## Level 3: 6 nodes to be scored (1825 eliminated genes)##
## Level 2: 2 nodes to be scored (4245 eliminated genes)##
## Level 1: 1 nodes to be scored (9690 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 24 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1016 GO terms found. )##
## Build GO DAG topology ..........## ( 2409 GO terms and 4679 relations. )##
## Annotating nodes ...............## ( 19139 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 247 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 11: 3 nodes to be scored (0 eliminated genes)##
## Level 10: 9 nodes to be scored (0 eliminated genes)##
## Level 9: 16 nodes to be scored (151 eliminated genes)##
## Level 8: 29 nodes to be scored (313 eliminated genes)##
## Level 7: 40 nodes to be scored (2522 eliminated genes)##
## Level 6: 38 nodes to be scored (3849 eliminated genes)##
## Level 5: 44 nodes to be scored (6866 eliminated genes)##
## Level 4: 32 nodes to be scored (8581 eliminated genes)##
## Level 3: 27 nodes to be scored (16019 eliminated genes)##
## Level 2: 8 nodes to be scored (18122 eliminated genes)##
## Level 1: 1 nodes to be scored (18811 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 247 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 211 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 12: 1 nodes to be scored (0 eliminated genes)##
## Level 11: 1 nodes to be scored (0 eliminated genes)##
## Level 10: 9 nodes to be scored (82 eliminated genes)##
## Level 9: 16 nodes to be scored (82 eliminated genes)##
## Level 8: 26 nodes to be scored (565 eliminated genes)##
## Level 7: 34 nodes to be scored (2412 eliminated genes)##
## Level 6: 30 nodes to be scored (4072 eliminated genes)##
## Level 5: 35 nodes to be scored (7554 eliminated genes)##
## Level 4: 32 nodes to be scored (9107 eliminated genes)##
## Level 3: 21 nodes to be scored (14716 eliminated genes)##
## Level 2: 5 nodes to be scored (18274 eliminated genes)##
## Level 1: 1 nodes to be scored (18752 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 211 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 1187 GO terms found. )##
## Build GO DAG topology ..........## ( 1615 GO terms and 2106 relations. )##
## Annotating nodes ...............## ( 28500 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 194 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 10: 1 nodes to be scored (0 eliminated genes)##
## Level 9: 6 nodes to be scored (0 eliminated genes)##
## Level 8: 15 nodes to be scored (78 eliminated genes)##
## Level 7: 25 nodes to be scored (4076 eliminated genes)##
## Level 6: 34 nodes to be scored (6457 eliminated genes)##
## Level 5: 43 nodes to be scored (8023 eliminated genes)##
## Level 4: 38 nodes to be scored (10603 eliminated genes)##
## Level 3: 21 nodes to be scored (17034 eliminated genes)##
## Level 2: 10 nodes to be scored (19446 eliminated genes)##
## Level 1: 1 nodes to be scored (27263 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 194 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 168 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 2 nodes to be scored (0 eliminated genes)##
## Level 8: 8 nodes to be scored (0 eliminated genes)##
## Level 7: 17 nodes to be scored (3820 eliminated genes)##
## Level 6: 31 nodes to be scored (5677 eliminated genes)##
## Level 5: 42 nodes to be scored (6902 eliminated genes)##
## Level 4: 38 nodes to be scored (10148 eliminated genes)##
## Level 3: 18 nodes to be scored (15850 eliminated genes)##
## Level 2: 11 nodes to be scored (18728 eliminated genes)##
## Level 1: 1 nodes to be scored (27026 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 168 nontrivial nodes
## parameters:
## test statistic: fisher
##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## Building most specific GOs .....## ( 337 GO terms found. )##
## Build GO DAG topology ..........## ( 554 GO terms and 952 relations. )##
## Annotating nodes ...............## ( 10145 genes annotated to the GO terms. )##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 43 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 9: 3 nodes to be scored (0 eliminated genes)##
## Level 8: 5 nodes to be scored (0 eliminated genes)##
## Level 7: 5 nodes to be scored (166 eliminated genes)##
## Level 6: 6 nodes to be scored (402 eliminated genes)##
## Level 5: 6 nodes to be scored (673 eliminated genes)##
## Level 4: 7 nodes to be scored (2731 eliminated genes)##
## Level 3: 8 nodes to be scored (3824 eliminated genes)##
## Level 2: 2 nodes to be scored (4768 eliminated genes)##
## Level 1: 1 nodes to be scored (9881 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 43 nontrivial nodes
## parameters:
## test statistic: fisher
##
## -- Weight01 Algorithm --
##
## the algorithm is scoring 36 nontrivial nodes
## parameters:
## test statistic: fisher##
## Level 8: 3 nodes to be scored (0 eliminated genes)##
## Level 7: 5 nodes to be scored (0 eliminated genes)##
## Level 6: 6 nodes to be scored (334 eliminated genes)##
## Level 5: 5 nodes to be scored (665 eliminated genes)##
## Level 4: 6 nodes to be scored (2478 eliminated genes)##
## Level 3: 8 nodes to be scored (3647 eliminated genes)##
## Level 2: 2 nodes to be scored (4296 eliminated genes)##
## Level 1: 1 nodes to be scored (9943 eliminated genes)##
## -- Classic Algorithm --
##
## the algorithm is scoring 36 nontrivial nodes
## parameters:
## test statistic: fisher
3 ClusterProfiler analysis
3.1 Plant
3.1.1 Import des données pour l’analyse TopGO sur les échantillons issus des plantes
# Définir la liste des conditions d’intérêt
select_cond <- c(
"P_t1_Q11L, P_t1_Q11V_L",
"P_t1_Q21L, P_t1_Q21V_L",
"P_t2_Q11L, P_t2_Q11V_L",
"P_t2_Q21L, P_t2_Q21V_L",
"P_t1_Q11V_L, P_t2_Q11V_L",
"P_t1_Q21V_L, P_t2_Q21V_L",
"P_t1_Q11L, P_t2_Q11L",
"P_t1_Q21L, P_t2_Q21L",
"P_t1_Q11L, P_t1_Q21L",
"P_t1_Q11V_L, P_t1_Q21V_L",
"P_t2_Q11L, P_t2_Q21L",
"P_t2_Q11V_L, P_t2_Q21V_L"
)
# Lire les lignes du fichier contenant les chemins et infos
lines_raw <- readLines("TopGO/Plant/liste_deseq.txt")## Warning in readLines("TopGO/Plant/liste_deseq.txt"): ligne finale incomplète
## trouvée dans 'TopGO/Plant/liste_deseq.txt'# Initialiser une liste de résultats
chemins_trouves <- data.frame(ID1 = character(),
ID2 = character(),
chemin = character(),
info = character(),
stringsAsFactors = FALSE)
# Recherche des lignes correspondantes à chaque couple
for (cond in select_cond) {
ids <- str_split(cond, ",\\s*")[[1]]
id1 <- ids[1]
id2 <- ids[2]
# Match la ligne contenant les deux identifiants dans le nom du fichier
match_lines <- lines_raw[str_detect(lines_raw, fixed(id1)) &
str_detect(lines_raw, fixed(id2))]
for (line in match_lines) {
# Séparer le chemin et l'info
parts <- str_split(line, ",\\s*")[[1]]
chemin <- parts[1]
info <- ifelse(length(parts) > 1, parts[2], NA)
if (!is.na(chemin) && file.exists(chemin)) {
chemins_trouves <- rbind(
chemins_trouves,
data.frame(ID1 = id1, ID2 = id2, chemin = chemin, info = info,
stringsAsFactors = FALSE)
)
} else {
warning(paste("Fichier introuvable ou chemin invalide:", chemin))
}
}
}
# Importer et annoter les tableaux
list_tables <- list()
for (i in 1:nrow(chemins_trouves)) {
path <- chemins_trouves$chemin[i]
id_label <- paste(chemins_trouves$ID1[i], chemins_trouves$ID2[i],
sep = "_VS_")
info_val <- chemins_trouves$info[i]
df <- tryCatch({
read_delim(path, delim = ",", show_col_types = FALSE)
}, error = function(e) {
warning(paste("Erreur lors de l'import:", path))
return(NULL)
})
if (!is.null(df)) {
df$ID <- id_label
df$Info <- info_val
df_2 <- subset(df,padj < 0.05 & abs(log2FoldChange) > 1 & padj != 0)
#use subset to filter dataframes by columns
list_tables[[length(list_tables) + 1]] <- df_2
}
}## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## • `` -> `...1`# Fusionner tous les tableaux
table_fusionnee <- bind_rows(list_tables)
colnames(table_fusionnee)[1] <- "gene_id"
# Aperçu ou sauvegarde
print(head(table_fusionnee))## # A tibble: 6 × 9
## gene_id baseMean log2FoldChange lfcSE stat pvalue padj ID Info
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 lcl|NC_090… 105. -21.7 2.01 -10.8 4.38e-27 1.56e-22 P_t1… Plant
## 2 lcl|NC_090… 60.1 22.4 2.18 10.3 9.43e-25 1.69e-20 P_t1… Plant
## 3 lcl|NC_090… 51.3 23.3 2.44 9.53 1.60e-21 1.91e-17 P_t1… Plant
## 4 lcl|NC_090… 26.6 -18.9 2.10 -8.97 2.96e-19 2.64e-15 P_t1… Plant
## 5 lcl|NC_090… 196. 26.4 2.97 8.91 5.03e-19 3.59e-15 P_t1… Plant
## 6 lcl|NC_090… 23.2 -19.8 2.36 -8.39 5.02e-17 2.56e-13 P_t1… Plant#write_csv(table_fusionnee, "TopGO/Plant/table_fusionnee.csv")
# Mapping gènes → KO
ko_map <- read.delim("TopGO/resultats_concat_final_kegg.tsv", header = TRUE)
table_fusionnee$KO <- NA
# Pour chaque ligne de ko_table,
#on cherche l'identifiant dans les gene_id de deg_ko
for(i in seq_len(nrow(ko_map))) {
pattern <- ko_map$gene_id[i]
match_index <- str_detect(table_fusionnee$gene_id, fixed(pattern))
# Vérifier si on a trouvé une correspondance avant d'affecter une valeur
if (any(match_index)) {
table_fusionnee$KO[match_index] <- ko_map$ko[i]
}
}3.1.2 Formalisations des données, tests et représentations graphiques
## Reading KEGG annotation online: "https://rest.kegg.jp/link/ko/pathway"...## Reading KEGG annotation online: "https://rest.kegg.jp/list/pathway/ko"...
3.2 Insect
3.2.1 Import des données pour l’analyse TopGO sur les échantillons issus des plantes
# Définir la liste des conditions d’intérêt
select_cond=c("B_t1_Q11L, B_t1_Q11V_L", "B_t1_Q21L, B_t1_Q21V_L", "B_t2_Q11L,
B_t2_Q11V_L", "B_t2_Q21L, B_t2_Q21V_L", "B_t1_Q11V_L,
B_t2_Q11V_L", "B_t1_Q21V_L, B_t2_Q21V_L", "B_t1_Q11L, B_t2_Q11L",
"B_t1_Q21L, B_t2_Q21L", "B_t1_Q11L, B_t1_Q21L", "B_t1_Q11V_L,
B_t1_Q21V_L", "B_t2_Q11L, B_t2_Q21L", "B_t2_Q11V_L, B_t2_Q21V_L")
# Lire les lignes du fichier contenant les chemins et infos
lines_raw <- readLines("TopGO/Insect/liste_deseq.txt")
# Initialiser une liste de résultats
chemins_trouves <- data.frame(ID1 = character(),
ID2 = character(),
chemin = character(),
info = character(),
stringsAsFactors = FALSE)
# Recherche des lignes correspondantes à chaque couple
for (cond in select_cond) {
ids <- str_split(cond, ",\\s*")[[1]]
id1 <- ids[1]
id2 <- ids[2]
# Match la ligne contenant les deux identifiants dans le nom du fichier
match_lines <- lines_raw[str_detect(lines_raw, fixed(id1)) &
str_detect(lines_raw, fixed(id2))]
for (line in match_lines) {
# Séparer le chemin et l'info
parts <- str_split(line, ",\\s*")[[1]]
chemin <- parts[1]
info <- ifelse(length(parts) > 1, parts[2], NA)
if (!is.na(chemin) && file.exists(chemin)) {
chemins_trouves <- rbind(
chemins_trouves,
data.frame(ID1 = id1, ID2 = id2, chemin = chemin, info = info,
stringsAsFactors = FALSE)
)
} else {
warning(paste("Fichier introuvable ou chemin invalide:", chemin))
}
}
}
# Importer et annoter les tableaux
list_tables <- list()
for (i in 1:nrow(chemins_trouves)) {
path <- chemins_trouves$chemin[i]
id_label <- paste(chemins_trouves$ID1[i], chemins_trouves$ID2[i],
sep = "_VS_")
info_val <- chemins_trouves$info[i]
df <- tryCatch({
read_delim(path, delim = ",", show_col_types = FALSE)
}, error = function(e) {
warning(paste("Erreur lors de l'import:", path))
return(NULL)
})
if (!is.null(df)) {
df$ID <- id_label
df$Info <- info_val
df_2 <- subset(df,padj < 0.05 & abs(log2FoldChange) > 1 & padj != 0)
#use subset to filter dataframes by columns
list_tables[[length(list_tables) + 1]] <- df_2
}
}## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## New names:
## • `` -> `...1`# Fusionner tous les tableaux
table_fusionnee <- bind_rows(list_tables)
colnames(table_fusionnee)[1] <- "gene_id"
# Aperçu ou sauvegarde
print(head(table_fusionnee))## # A tibble: 6 × 9
## gene_id baseMean log2FoldChange lfcSE stat pvalue padj ID Info
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 lcl|NC_092… 134. -20.7 1.54 -13.4 4.49e-41 1.03e-36 B_t1… Inse…
## 2 lcl|NC_092… 17.9 -18.3 2.04 -8.98 2.64e-19 3.04e-15 B_t1… Inse…
## 3 lcl|NC_092… 76.1 -19.2 2.30 -8.32 8.53e-17 6.55e-13 B_t1… Inse…
## 4 lcl|NC_092… 43.0 22.9 2.76 8.28 1.27e-16 7.30e-13 B_t1… Inse…
## 5 lcl|NC_092… 36.6 -20.2 2.59 -7.79 6.45e-15 2.97e-11 B_t1… Inse…
## 6 lcl|NC_092… 59.8 22.6 3.03 7.47 7.83e-14 3.01e-10 B_t1… Inse…#write_csv(table_fusionnee, "TopGO/Insect/table_fusionnee.csv")
# Mapping gènes → KO
ko_map <- read.delim("TopGO/resultats_concat_final_kegg.tsv", header = TRUE)
table_fusionnee$KO <- NA
# Pour chaque ligne de ko_table,
#on cherche l'identifiant dans les gene_id de deg_ko
for(i in seq_len(nrow(ko_map))) {
pattern <- ko_map$gene_id[i]
match_index <- str_detect(table_fusionnee$gene_id, fixed(pattern))
# Vérifier si on a trouvé une correspondance avant d'affecter une valeur
if (any(match_index)) {
table_fusionnee$KO[match_index] <- ko_map$ko[i]
}
}3.2.2 Formalisations des données, tests et représentations graphiques
#UpSetR
##Plant
###Formalisation des données UpsetR
# Liste de comparaison
select_cond <- c("P_t1_Q11L, P_t1_Q11V_L", "P_t1_Q21L, P_t1_Q21V_L", "P_t2_Q11L,
P_t2_Q11V_L", "P_t2_Q21L, P_t2_Q21V_L", "P_t1_Q11V_L,
P_t2_Q11V_L", "P_t1_Q21V_L, P_t2_Q21V_L", "P_t1_Q11L,
P_t2_Q11L", "P_t1_Q21L, P_t2_Q21L", "P_t1_Q11L, P_t1_Q21L",
"P_t1_Q11V_L, P_t1_Q21V_L", "P_t2_Q11L, P_t2_Q21L",
"P_t2_Q11V_L, P_t2_Q21V_L")
list_sig_genes <- list()
for (i in seq_along(select_cond)) {
ids <- strsplit(select_cond[i], ",\\s*")[[1]]
ID1 <- ids[1]
ID2 <- ids[2]
res.F <- results(dds_tomato.deseq, contrast = c("condition", ID1, ID2))
res.F$padj <- p.adjust(res.F$pvalue, method = "fdr")
res.F <- res.F[order(res.F$padj), ]
sig_genes_up <- rownames(res.F)[which(res.F$padj < 0.05 & res.F$log2FoldChange >= 1)]
sig_genes_down <- rownames(res.F)[which(res.F$padj < 0.05 & res.F$log2FoldChange <= -1)]
name_comp <- paste0(ID1, "_vs_", ID2)
df_up <- data.frame(gene = sig_genes_up, direction = "up", stringsAsFactors = FALSE)
df_down <- data.frame(gene = sig_genes_down, direction = "down", stringsAsFactors = FALSE)
list_sig_genes[[name_comp]] <- rbind(df_up, df_down)
}
# Obtenir tous les gènes significatifs
all_genes <- unique(unlist(lapply(list_sig_genes, function(df) df$gene)))
# Créer le tableau final
upset_data <- data.frame(gene = all_genes, stringsAsFactors = FALSE)
# Ajouter les colonnes de comparaison (1/0) et direction (par majorité si unique)
for (comp in names(list_sig_genes)) {
genes <- list_sig_genes[[comp]]
upset_data[[comp]] <- as.integer(upset_data$gene %in% genes$gene)
}
# Direction principale : si un gène est up ou down plus souvent
direction_vector <- sapply(upset_data$gene, function(g) {
dirs <- unlist(lapply(list_sig_genes, function(df) {
if (g %in% df$gene) df$direction[df$gene == g] else NULL
}))
if (length(dirs) == 0) return(NA)
if (sum(dirs == "up") >= sum(dirs == "down")) return("up") else return("down")
})
upset_data$direction <- factor(direction_vector, levels = c("up", "down"))
comparison_cols <- setdiff(colnames(upset_data), c("gene", "direction"))###Représentation graphique
#pdf("upset_plante.pdf")
ComplexUpset::upset(
upset_data,
intersect = comparison_cols,
base_annotations = list(
'Intersection size' = (
intersection_size(aes(fill = direction)) +
scale_fill_manual(values = c("up" = "red", "down" = "blue"))
)
),
min_size = 10,
# n_intersections = 20
)
#dev.off()##Insect
###Formalisation des données Upset
select_cond=c("B_t1_Q11L, B_t1_Q11V_L", "B_t1_Q21L, B_t1_Q21V_L", "B_t2_Q11L,
B_t2_Q11V_L", "B_t2_Q21L, B_t2_Q21V_L", "B_t1_Q11V_L,
B_t2_Q11V_L", "B_t1_Q21V_L, B_t2_Q21V_L", "B_t1_Q11L, B_t2_Q11L",
"B_t1_Q21L, B_t2_Q21L", "B_t1_Q11L, B_t1_Q21L", "B_t1_Q11V_L,
B_t1_Q21V_L", "B_t2_Q11L, B_t2_Q21L", "B_t2_Q11V_L, B_t2_Q21V_L")
list_sig_genes <- list()
for (i in seq_along(select_cond)) {
ids <- strsplit(select_cond[i], ",\\s*")[[1]]
ID1 <- ids[1]
ID2 <- ids[2]
res.F <- results(dds_bemisia.deseq, contrast = c("condition", ID1, ID2))
res.F$padj <- p.adjust(res.F$pvalue, method = "fdr")
res.F <- res.F[order(res.F$padj), ]
sig_genes_up <- rownames(res.F)[which(res.F$padj < 0.05 & res.F$log2FoldChange >= 1)]
sig_genes_down <- rownames(res.F)[which(res.F$padj < 0.05 & res.F$log2FoldChange <= -1)]
name_comp <- paste0(ID1, "_vs_", ID2)
df_up <- data.frame(gene = sig_genes_up, direction = "up", stringsAsFactors = FALSE)
df_down <- data.frame(gene = sig_genes_down, direction = "down", stringsAsFactors = FALSE)
list_sig_genes[[name_comp]] <- rbind(df_up, df_down)
}
# Obtenir tous les gènes significatifs
all_genes <- unique(unlist(lapply(list_sig_genes, function(df) df$gene)))
# Créer le tableau final
upset_data <- data.frame(gene = all_genes, stringsAsFactors = FALSE)
# Ajouter les colonnes de comparaison (1/0) et direction (par majorité si unique)
for (comp in names(list_sig_genes)) {
genes <- list_sig_genes[[comp]]
upset_data[[comp]] <- as.integer(upset_data$gene %in% genes$gene)
}
# Direction principale : si un gène est up ou down plus souvent
direction_vector <- sapply(upset_data$gene, function(g) {
dirs <- unlist(lapply(list_sig_genes, function(df) {
if (g %in% df$gene) df$direction[df$gene == g] else NULL
}))
if (length(dirs) == 0) return(NA)
if (sum(dirs == "up") >= sum(dirs == "down")) return("up") else return("down")
})
upset_data$direction <- factor(direction_vector, levels = c("up", "down"))
comparison_cols <- setdiff(colnames(upset_data), c("gene", "direction"))###Représentation graphique
#pdf("upset_insect.pdf")
ComplexUpset::upset(
upset_data,
intersect = comparison_cols,
base_annotations = list(
'Intersection size' = (
intersection_size(aes(fill = direction)) +
scale_fill_manual(values = c("up" = "red", "down" = "blue"))
)
),
min_size = 10,
# n_intersections = 20
)
#dev.off()